1871 lines
74 KiB
BibTeX
1871 lines
74 KiB
BibTeX
% Related
|
|
|
|
@article{lialin2023scaling,
|
|
title={Scaling down to scale up: A guide to parameter-efficient fine-tuning},
|
|
author={Lialin, Vladislav and Deshpande, Vijeta and Rumshisky, Anna},
|
|
journal={arXiv preprint arXiv:2303.15647},
|
|
year={2023}
|
|
}
|
|
% SDCTFT
|
|
@article{shen2024parameter,
|
|
title={Parameter-efficient fine-tuning via selective discrete cosine transform},
|
|
author={Shen, Yixian and Bi, Qi and Huang, Jia-Hong and Zhu, Hongyi and Pathania, Anuj},
|
|
journal={arXiv preprint arXiv:2410.09103},
|
|
year={2024}
|
|
}
|
|
|
|
|
|
% Freq
|
|
@article{gao2024parameter,
|
|
title={Parameter-efficient fine-tuning with discrete fourier transform},
|
|
author={Gao, Ziqi and Wang, Qichao and Chen, Aochuan and Liu, Zijing and Wu, Bingzhe and Chen, Liang and Li, Jia},
|
|
journal={arXiv preprint arXiv:2405.03003},
|
|
year={2024}
|
|
}
|
|
@article{hu2025waveletft,
|
|
title={WaveletFT: Discrete wavelet transform for parameter-efficient fine-tuning},
|
|
author={Hu, Can and Yang, Jie and Song, Shien and Fan, Wentao and Xie, Tao},
|
|
journal={Neurocomputing},
|
|
pages={130765},
|
|
year={2025},
|
|
publisher={Elsevier}
|
|
}
|
|
% Little Wavelet
|
|
@article{bilican2025exploring,
|
|
title={Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets},
|
|
author={Bilican, Ahmet and Y{\i}lmaz, M Ak{\i}n and Tekalp, A Murat and Cinbi{\c{s}}, R G{\"o}kberk},
|
|
journal={arXiv preprint arXiv:2505.12532},
|
|
year={2025}
|
|
}
|
|
@article{zhang2025f,
|
|
title={F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning},
|
|
author={Zhang, Hangwei and Kang, Chun and Wang, Yan and Zou, Difan},
|
|
journal={arXiv preprint arXiv:2509.23173},
|
|
year={2025}
|
|
}
|
|
|
|
|
|
% LoCA
|
|
@article{du2025loca,
|
|
title={LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning},
|
|
author={Du, Zhekai and Min, Yinjie and Li, Jingjing and Lu, Ke and Zou, Changliang and Peng, Liuhua and Chu, Tingjin and Gong, Mingming},
|
|
journal={arXiv preprint arXiv:2502.06820},
|
|
year={2025}
|
|
}
|
|
% Flylora
|
|
@article{zou2025flylora,
|
|
title={FlyloRA: Boosting task decoupling and parameter efficiency via implicit rank-wise mixture-of-experts},
|
|
author={Zou, Heming and Zang, Yunliang and Xu, Wutong and Zhu, Yao and Ji, Xiangyang},
|
|
journal={arXiv preprint arXiv:2510.08396},
|
|
year={2025}
|
|
}
|
|
|
|
|
|
% LLM
|
|
@misc{qwen3technicalreport,
|
|
title={Qwen3 Technical Report},
|
|
author={Qwen Team},
|
|
year={2025},
|
|
eprint={2505.09388},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2505.09388},
|
|
}
|
|
@article{grattafiori2024llama,
|
|
title={The llama 3 herd of models},
|
|
author={Grattafiori, Aaron and Dubey, Abhimanyu and Jauhri, Abhinav and Pandey, Abhinav and Kadian, Abhishek and Al-Dahle, Ahmad and Letman, Aiesha and Mathur, Akhil and Schelten, Alan and Vaughan, Alex and others},
|
|
journal={arXiv preprint arXiv:2407.21783},
|
|
year={2024}
|
|
}
|
|
@article{gemma_2025,
|
|
title={Gemma 3},
|
|
url={https://goo.gle/Gemma3Report},
|
|
publisher={Kaggle},
|
|
author={Gemma Team},
|
|
year={2025}
|
|
}
|
|
|
|
% IJCAI
|
|
@article{han2024parameter,
|
|
title={Parameter-efficient fine-tuning for large models: A comprehensive survey},
|
|
author={Han, Zeyu and Gao, Chao and Liu, Jinyang and Zhang, Jeff and Zhang, Sai Qian},
|
|
journal={arXiv preprint arXiv:2403.14608},
|
|
year={2024}
|
|
}
|
|
@inproceedings{shiracite,
|
|
author = {Bhardwaj, Kartikeya and Pandey, Nilesh Prasad and Priyadarshi, Sweta and Ganapathy, Viswanath and Kadambi, Shreya and Esteves, Rafael and Borse, Shubhankar and Whatmough, Paul and Garrepalli, Risheek and Van Baalen, Mart and Teague, Harris and Nagel, Markus},
|
|
title = {Sparse high rank adapters},
|
|
year = {2024},
|
|
isbn = {9798331314385},
|
|
publisher = {Curran Associates Inc.},
|
|
address = {Red Hook, NY, USA},
|
|
booktitle = {Proceedings of the 38th International Conference on Neural Information Processing Systems},
|
|
articleno = {438},
|
|
numpages = {31},
|
|
location = {Vancouver, BC, Canada},
|
|
series = {NIPS '24}
|
|
}
|
|
@article{hu2021lora,
|
|
title={Lora: Low-rank adaptation of large language models},
|
|
author={Hu, Edward J and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu},
|
|
journal={arXiv preprint arXiv:2106.09685},
|
|
year={2021}
|
|
}
|
|
|
|
% adapter
|
|
@inproceedings{houlsby2019parameter,
|
|
title={Parameter-efficient transfer learning for NLP},
|
|
author={Houlsby, Neil and Giurgiu, Andrei and Jastrzebski, Stanislaw and Morrone, Bruna and De Laroussilhe, Quentin and Gesmundo, Andrea and Attariyan, Mona and Gelly, Sylvain},
|
|
booktitle={International conference on machine learning},
|
|
pages={2790--2799},
|
|
year={2019},
|
|
organization={PMLR}
|
|
}
|
|
|
|
% AAAING
|
|
|
|
% Datasets
|
|
% GSM8K
|
|
@article{cobbe2021training,
|
|
title={Training verifiers to solve math word problems},
|
|
author={Cobbe, Karl and Kosaraju, Vineet and Bavarian, Mohammad and Chen, Mark and Jun, Heewoo and Kaiser, Lukasz and Plappert, Matthias and Tworek, Jerry and Hilton, Jacob and Nakano, Reiichiro and others},
|
|
journal={arXiv preprint arXiv:2110.14168},
|
|
year={2021}
|
|
}
|
|
% SVAMP
|
|
@article{patel2021nlp,
|
|
title={Are NLP models really able to solve simple math word problems?},
|
|
author={Patel, Arkil and Bhattamishra, Satwik and Goyal, Navin},
|
|
journal={arXiv preprint arXiv:2103.07191},
|
|
year={2021}
|
|
}
|
|
% MultiArith
|
|
@article{roy2016solving,
|
|
title={Solving general arithmetic word problems},
|
|
author={Roy, Subhro and Roth, Dan},
|
|
journal={arXiv preprint arXiv:1608.01413},
|
|
year={2016}
|
|
}
|
|
% Addsub
|
|
@inproceedings{hosseini2014learning,
|
|
title={Learning to solve arithmetic word problems with verb categorization},
|
|
author={Hosseini, Mohammad Javad and Hajishirzi, Hannaneh and Etzioni, Oren and Kushman, Nate},
|
|
booktitle={Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
|
|
pages={523--533},
|
|
year={2014}
|
|
}
|
|
% AQuA
|
|
@article{ling2017program,
|
|
title={Program induction by rationale generation: Learning to solve and explain algebraic word problems},
|
|
author={Ling, Wang and Yogatama, Dani and Dyer, Chris and Blunsom, Phil},
|
|
journal={arXiv preprint arXiv:1705.04146},
|
|
year={2017}
|
|
}
|
|
% SingleEq
|
|
@article{koncel2015parsing,
|
|
title={Parsing algebraic word problems into equations},
|
|
author={Koncel-Kedziorski, Rik and Hajishirzi, Hannaneh and Sabharwal, Ashish and Etzioni, Oren and Ang, Siena Dumas},
|
|
journal={Transactions of the Association for Computational Linguistics},
|
|
volume={3},
|
|
pages={585--597},
|
|
year={2015},
|
|
publisher={MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info~…}
|
|
}
|
|
% MAWPS
|
|
@inproceedings{koncel2016mawps,
|
|
title={MAWPS: A math word problem repository},
|
|
author={Koncel-Kedziorski, Rik and Roy, Subhro and Amini, Aida and Kushman, Nate and Hajishirzi, Hannaneh},
|
|
booktitle={Proceedings of the 2016 conference of the north american chapter of the association for computational linguistics: human language technologies},
|
|
pages={1152--1157},
|
|
year={2016}
|
|
}
|
|
% BoolQ
|
|
@article{clark2019boolq,
|
|
title={Boolq: Exploring the surprising difficulty of natural yes/no questions},
|
|
author={Clark, Christopher and Lee, Kenton and Chang, Ming-Wei and Kwiatkowski, Tom and Collins, Michael and Toutanova, Kristina},
|
|
journal={arXiv preprint arXiv:1905.10044},
|
|
year={2019}
|
|
}
|
|
% PIQA
|
|
@inproceedings{bisk2020piqa,
|
|
title={Piqa: Reasoning about physical commonsense in natural language},
|
|
author={Bisk, Yonatan and Zellers, Rowan and Gao, Jianfeng and Choi, Yejin and others},
|
|
booktitle={Proceedings of the AAAI conference on artificial intelligence},
|
|
volume={34},
|
|
number={05},
|
|
pages={7432--7439},
|
|
year={2020}
|
|
}
|
|
% SIQA
|
|
@article{sap2019socialiqa,
|
|
title={Socialiqa: Commonsense reasoning about social interactions},
|
|
author={Sap, Maarten and Rashkin, Hannah and Chen, Derek and LeBras, Ronan and Choi, Yejin},
|
|
journal={arXiv preprint arXiv:1904.09728},
|
|
year={2019}
|
|
}
|
|
% HW
|
|
@article{zellers2019hellaswag,
|
|
title={Hellaswag: Can a machine really finish your sentence?},
|
|
author={Zellers, Rowan and Holtzman, Ari and Bisk, Yonatan and Farhadi, Ali and Choi, Yejin},
|
|
journal={arXiv preprint arXiv:1905.07830},
|
|
year={2019}
|
|
}
|
|
% WN
|
|
@inproceedings{sakaguchi2020winogrande,
|
|
title={Winogrande: An adversarial winograd schema challenge at scale},
|
|
author={Sakaguchi, Keisuke and Le Bras, Ronan and Bhagavatula, Chandra and Choi, Yejin},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={34},
|
|
number={05},
|
|
pages={8732--8740},
|
|
year={2020}
|
|
}
|
|
% ARC
|
|
@article{clark2018think,
|
|
title={Think you have solved question answering? try arc, the ai2 reasoning challenge},
|
|
author={Clark, Peter and Cowhey, Isaac and Etzioni, Oren and Khot, Tushar and Sabharwal, Ashish and Schoenick, Carissa and Tafjord, Oyvind},
|
|
journal={arXiv preprint arXiv:1803.05457},
|
|
year={2018}
|
|
}
|
|
% OBDA
|
|
@article{mihaylov2018can,
|
|
title={Can a suit of armor conduct electricity? a new dataset for open book question answering},
|
|
author={Mihaylov, Todor and Clark, Peter and Khot, Tushar and Sabharwal, Ashish},
|
|
journal={arXiv preprint arXiv:1809.02789},
|
|
year={2018}
|
|
}
|
|
|
|
% Related
|
|
|
|
@article{li2021prefix,
|
|
title={Prefix-tuning: Optimizing continuous prompts for generation},
|
|
author={Li, Xiang Lisa and Liang, Percy},
|
|
journal={arXiv preprint arXiv:2101.00190},
|
|
year={2021}
|
|
}
|
|
@article{dong2025attention,
|
|
title={Attention Retrieves, MLP Memorizes: Disentangling Trainable Components in the Transformer},
|
|
author={Dong, Yihe and Noci, Lorenzo and Khodak, Mikhail and Li, Mufan},
|
|
journal={arXiv preprint arXiv:2506.01115},
|
|
year={2025}
|
|
}
|
|
@article{michel2019sixteen,
|
|
title={Are sixteen heads really better than one?},
|
|
author={Michel, Paul and Levy, Omer and Neubig, Graham},
|
|
journal={Advances in neural information processing systems},
|
|
volume={32},
|
|
year={2019}
|
|
}
|
|
@article{belinkov2018evaluating,
|
|
title={Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks},
|
|
author={Belinkov, Yonatan and M{\`a}rquez, Llu{\'\i}s and Sajjad, Hassan and Durrani, Nadir and Dalvi, Fahim and Glass, James},
|
|
journal={arXiv preprint arXiv:1801.07772},
|
|
year={2018}
|
|
}
|
|
% Others
|
|
@article{ding2023parameter,
|
|
title={Parameter-efficient fine-tuning of large-scale pre-trained language models},
|
|
author={Ding, Ning and Qin, Yujia and Yang, Guang and Wei, Fuchao and Yang, Zonghan and Su, Yusheng and Hu, Shengding and Chen, Yulin and Chan, Chi-Min and Chen, Weize and others},
|
|
journal={Nature machine intelligence},
|
|
volume={5},
|
|
number={3},
|
|
pages={220--235},
|
|
year={2023},
|
|
publisher={Nature Publishing Group UK London}
|
|
}
|
|
@article{peng2023instruction,
|
|
title={Instruction tuning with gpt-4},
|
|
author={Peng, Baolin and Li, Chunyuan and He, Pengcheng and Galley, Michel and Gao, Jianfeng},
|
|
journal={arXiv preprint arXiv:2304.03277},
|
|
year={2023}
|
|
}
|
|
|
|
% Baselines
|
|
@article{liu2024dora,
|
|
title={Dora: Weight-decomposed low-rank adaptation},
|
|
author={Liu, Shih-Yang and Wang, Chien-Yi and Yin, Hongxu and Molchanov, Pavlo and Wang, Yu-Chiang Frank and Cheng, Kwang-Ting and Chen, Min-Hung},
|
|
journal={arXiv preprint arXiv:2402.09353},
|
|
year={2024}
|
|
}
|
|
|
|
@article{zhang2023adalora,
|
|
title={Adalora: Adaptive budget allocation for parameter-efficient fine-tuning},
|
|
author={Zhang, Qingru and Chen, Minshuo and Bukharin, Alexander and Karampatziakis, Nikos and He, Pengcheng and Cheng, Yu and Chen, Weizhu and Zhao, Tuo},
|
|
journal={arXiv preprint arXiv:2303.10512},
|
|
year={2023}
|
|
}
|
|
% C3A
|
|
@article{chen2024parameter,
|
|
title={Parameter-efficient fine-tuning via circular convolution},
|
|
author={Chen, Aochuan and Cheng, Jiashun and Liu, Zijing and Gao, Ziqi and Tsung, Fugee and Li, Yu and Li, Jia},
|
|
journal={arXiv preprint arXiv:2407.19342},
|
|
year={2024}
|
|
}
|
|
% BONE
|
|
@article{kang2024balancing,
|
|
title={Balancing LoRA Performance and Efficiency with Simple Shard Sharing},
|
|
author={Kang, Jiale and Yin, Qingyu},
|
|
journal={arXiv preprint arXiv:2409.15371},
|
|
year={2024}
|
|
}
|
|
% VERA-EDITED
|
|
@article{kopiczko2023vera,
|
|
title={Vera: Vector-based random matrix adaptation},
|
|
author={{Kopiczko et al.}},
|
|
journal={arXiv preprint arXiv:2310.11454},
|
|
year={2023}
|
|
}
|
|
% BOFT
|
|
@article{liu2023parameter,
|
|
title={Parameter-efficient orthogonal finetuning via butterfly factorization},
|
|
author={Liu, Weiyang and Qiu, Zeju and Feng, Yao and Xiu, Yuliang and Xue, Yuxuan and Yu, Longhui and Feng, Haiwen and Liu, Zhen and Heo, Juyeon and Peng, Songyou and others},
|
|
journal={arXiv preprint arXiv:2311.06243},
|
|
year={2023}
|
|
}
|
|
% LN-Tuning
|
|
@article{zhao2023tuning,
|
|
title={Tuning layernorm in attention: Towards efficient multi-modal llm finetuning},
|
|
author={Zhao, Bingchen and Tu, Haoqin and Wei, Chen and Mei, Jieru and Xie, Cihang},
|
|
journal={arXiv preprint arXiv:2312.11420},
|
|
year={2023}
|
|
}
|
|
|
|
% Deepspeed
|
|
@inproceedings{rasley2020deepspeed,
|
|
title={Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters},
|
|
author={Rasley, Jeff and Rajbhandari, Samyam and Ruwase, Olatunji and He, Yuxiong},
|
|
booktitle={Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery \& data mining},
|
|
pages={3505--3506},
|
|
year={2020}
|
|
}
|
|
% Huggingface Transformers
|
|
@inproceedings{wolf2020transformers,
|
|
title={Transformers: State-of-the-art natural language processing},
|
|
author={Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien and Delangue, Clement and Moi, Anthony and Cistac, Pierric and Rault, Tim and Louf, Remi and Funtowicz, Morgan and others},
|
|
booktitle={Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations},
|
|
pages={38--45},
|
|
year={2020}
|
|
}
|
|
|
|
@inproceedings{geva2021transformer,
|
|
title={Transformer Feed-Forward Layers Are Key-Value Memories},
|
|
author={Geva, Mor and Schuster, Roei and Berant, Jonathan and Levy, Omer},
|
|
booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
|
|
pages={5484--5495},
|
|
year={2021}
|
|
}
|
|
|
|
@article{su2024roformer,
|
|
title={Roformer: Enhanced transformer with rotary position embedding},
|
|
author={Su, Jianlin and Ahmed, Murtadha and Lu, Yu and Pan, Shengfeng and Bo, Wen and Liu, Yunfeng},
|
|
journal={Neurocomputing},
|
|
volume={568},
|
|
pages={127063},
|
|
year={2024},
|
|
publisher={Elsevier}
|
|
}
|
|
@article{barbero2024round,
|
|
title={Round and round we go! what makes rotary positional encodings useful?},
|
|
author={Barbero, Federico and Vitvitskyi, Alex and Perivolaropoulos, Christos and Pascanu, Razvan and Veli{\v{c}}kovi{\'c}, Petar},
|
|
journal={arXiv preprint arXiv:2410.06205},
|
|
year={2024}
|
|
}
|
|
|
|
@article{jin2025massive,
|
|
title={Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding},
|
|
author={Jin, Mingyu and Mei, Kai and Xu, Wujiang and Sun, Mingjie and Tang, Ruixiang and Du, Mengnan and Liu, Zirui and Zhang, Yongfeng},
|
|
journal={arXiv preprint arXiv:2502.01563},
|
|
year={2025}
|
|
}
|
|
@article{vaswani2017attention,
|
|
title={Attention is all you need},
|
|
author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
|
|
journal={Advances in neural information processing systems},
|
|
volume={30},
|
|
year={2017}
|
|
}
|
|
@article{touvron2023llama,
|
|
title={Llama: Open and efficient foundation language models},
|
|
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},
|
|
journal={arXiv preprint arXiv:2302.13971},
|
|
year={2023}
|
|
}
|
|
@article{shazeer2020glu,
|
|
title={Glu variants improve transformer},
|
|
author={Shazeer, Noam},
|
|
journal={arXiv preprint arXiv:2002.05202},
|
|
year={2020}
|
|
}
|
|
@inproceedings{he2016deep,
|
|
title={Deep residual learning for image recognition},
|
|
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
|
|
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
|
|
pages={770--778},
|
|
year={2016}
|
|
}
|
|
@article{bai2023qwen,
|
|
title={Qwen technical report},
|
|
author={Bai, Jinze and Bai, Shuai and Chu, Yunfei and Cui, Zeyu and Dang, Kai and Deng, Xiaodong and Fan, Yang and Ge, Wenbin and Han, Yu and Huang, Fei and others},
|
|
journal={arXiv preprint arXiv:2309.16609},
|
|
year={2023}
|
|
}
|
|
|
|
% SiLU
|
|
@article{elfwing2018sigmoid,
|
|
title={Sigmoid-weighted linear units for neural network function approximation in reinforcement learning},
|
|
author={Elfwing, Stefan and Uchibe, Eiji and Doya, Kenji},
|
|
journal={Neural networks},
|
|
volume={107},
|
|
pages={3--11},
|
|
year={2018},
|
|
publisher={Elsevier}
|
|
}
|
|
@article{ainslie2023gqa,
|
|
title={Gqa: Training generalized multi-query transformer models from multi-head checkpoints},
|
|
author={Ainslie, Joshua and Lee-Thorp, James and De Jong, Michiel and Zemlyanskiy, Yury and Lebr{\'o}n, Federico and Sanghai, Sumit},
|
|
journal={arXiv preprint arXiv:2305.13245},
|
|
year={2023}
|
|
}
|
|
@article{voita2019bottom,
|
|
title={The bottom-up evolution of representations in the transformer: A study with machine translation and language modeling objectives},
|
|
author={Voita, Elena and Sennrich, Rico and Titov, Ivan},
|
|
journal={arXiv preprint arXiv:1909.01380},
|
|
year={2019}
|
|
}
|
|
@article{hu2023llm,
|
|
title={Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models},
|
|
author={Hu, Zhiqiang and Wang, Lei and Lan, Yihuai and Xu, Wanyu and Lim, Ee-Peng and Bing, Lidong and Xu, Xing and Poria, Soujanya and Lee, Roy Ka-Wei},
|
|
journal={arXiv preprint arXiv:2304.01933},
|
|
year={2023}
|
|
}
|
|
@article{team2024gemma,
|
|
title={Gemma 2: Improving open language models at a practical size},
|
|
author={Team, Gemma and Riviere, Morgane and Pathak, Shreya and Sessa, Pier Giuseppe and Hardin, Cassidy and Bhupatiraju, Surya and Hussenot, L{\'e}onard and Mesnard, Thomas and Shahriari, Bobak and Ram{\'e}, Alexandre and others},
|
|
journal={arXiv preprint arXiv:2408.00118},
|
|
year={2024}
|
|
}
|
|
@article{dubey2024llama,
|
|
title={The llama 3 herd of models},
|
|
author={Dubey, Abhimanyu and Jauhri, Abhinav and Pandey, Abhinav and Kadian, Abhishek and Al-Dahle, Ahmad and Letman, Aiesha and Mathur, Akhil and Schelten, Alan and Yang, Amy and Fan, Angela and others},
|
|
journal={arXiv e-prints},
|
|
pages={arXiv--2407},
|
|
year={2024}
|
|
}
|
|
@article{team2024qwen2,
|
|
title={Qwen2 technical report},
|
|
author={Team, Qwen},
|
|
journal={arXiv preprint arXiv:2407.10671},
|
|
year={2024}
|
|
}
|
|
% Old
|
|
|
|
@article{sun2025stronger,
|
|
title={A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models},
|
|
author={Sun, Mengyang and Wang, Yihao and Feng, Tao and Zhang, Dan and Zhu, Yifan and Tang, Jie},
|
|
journal={arXiv preprint arXiv:2502.15828},
|
|
year={2025}
|
|
}
|
|
@article{pfeiffer2020mad,
|
|
title={Mad-x: An adapter-based framework for multi-task cross-lingual transfer},
|
|
author={Pfeiffer, Jonas and Vuli{\'c}, Ivan and Gurevych, Iryna and Ruder, Sebastian},
|
|
journal={arXiv preprint arXiv:2005.00052},
|
|
year={2020}
|
|
}
|
|
@article{raffel2020exploring,
|
|
title={Exploring the limits of transfer learning with a unified text-to-text transformer},
|
|
author={Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J},
|
|
journal={Journal of machine learning research},
|
|
volume={21},
|
|
number={140},
|
|
pages={1--67},
|
|
year={2020}
|
|
}
|
|
@article{zaken2021bitfit,
|
|
title={Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models},
|
|
author={Zaken, Elad Ben and Ravfogel, Shauli and Goldberg, Yoav},
|
|
journal={arXiv preprint arXiv:2106.10199},
|
|
year={2021}
|
|
}
|
|
@inproceedings{papineni2002bleu,
|
|
title={Bleu: a method for automatic evaluation of machine translation},
|
|
author={Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing},
|
|
booktitle={Proceedings of the 40th annual meeting of the Association for Computational Linguistics},
|
|
pages={311--318},
|
|
year={2002}
|
|
}
|
|
@inproceedings{lin2004rouge,
|
|
title={Rouge: A package for automatic evaluation of summaries},
|
|
author={Lin, Chin-Yew},
|
|
booktitle={Text summarization branches out},
|
|
pages={74--81},
|
|
year={2004}
|
|
}
|
|
@article{jang2016categorical,
|
|
title={Categorical reparameterization with gumbel-softmax},
|
|
author={Jang, Eric and Gu, Shixiang and Poole, Ben},
|
|
journal={arXiv preprint arXiv:1611.01144},
|
|
year={2016}
|
|
}
|
|
@inproceedings{he2015delving,
|
|
title={Delving deep into rectifiers: Surpassing human-level performance on imagenet classification},
|
|
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
|
|
booktitle={Proceedings of the IEEE international conference on computer vision},
|
|
pages={1026--1034},
|
|
year={2015}
|
|
}
|
|
@article{guo2025nlora,
|
|
title={NLoRA: Nystr$\backslash$" om-Initiated Low-Rank Adaptation for Large Language Models},
|
|
author={Guo, Chenlu and Wu, Yuan and Chang, Yi},
|
|
journal={arXiv preprint arXiv:2502.14482},
|
|
year={2025}
|
|
}
|
|
|
|
@article{ba2016layer,
|
|
title={Layer normalization},
|
|
author={Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E},
|
|
journal={arXiv preprint arXiv:1607.06450},
|
|
year={2016}
|
|
}
|
|
|
|
@article{team2023gemini,
|
|
title={Gemini: a family of highly capable multimodal models},
|
|
author={Team, Gemini and Anil, Rohan and Borgeaud, Sebastian and Alayrac, Jean-Baptiste and Yu, Jiahui and Soricut, Radu and Schalkwyk, Johan and Dai, Andrew M and Hauth, Anja and Millican, Katie and others},
|
|
journal={arXiv preprint arXiv:2312.11805},
|
|
year={2023}
|
|
}
|
|
@article{liu2023moelora,
|
|
title={Moelora: An moe-based parameter efficient fine-tuning method for multi-task medical applications},
|
|
author={Liu, Qidong and Wu, Xian and Zhao, Xiangyu and Zhu, Yuanshao and Xu, Derong and Tian, Feng and Zheng, Yefeng},
|
|
journal={arXiv preprint arXiv:2310.18339},
|
|
year={2023}
|
|
}
|
|
@article{wang2023multilora,
|
|
title={Multilora: Democratizing lora for better multi-task learning},
|
|
author={Wang, Yiming and Lin, Yu and Zeng, Xiaodong and Zhang, Guannan},
|
|
journal={arXiv preprint arXiv:2311.11501},
|
|
year={2023}
|
|
}
|
|
@article{liu2021p,
|
|
title={P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks},
|
|
author={Liu, Xiao and Ji, Kaixuan and Fu, Yicheng and Tam, Weng Lam and Du, Zhengxiao and Yang, Zhilin and Tang, Jie},
|
|
journal={arXiv preprint arXiv:2110.07602},
|
|
year={2021}
|
|
}
|
|
@article{brown2020language,
|
|
title={Language models are few-shot learners},
|
|
author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
|
|
journal={Advances in neural information processing systems},
|
|
volume={33},
|
|
pages={1877--1901},
|
|
year={2020}
|
|
}
|
|
@article{liu2021conflict,
|
|
title={Conflict-averse gradient descent for multi-task learning},
|
|
author={Liu, Bo and Liu, Xingchao and Jin, Xiaojie and Stone, Peter and Liu, Qiang},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={34},
|
|
pages={18878--18890},
|
|
year={2021}
|
|
}
|
|
@article{navon2022multi,
|
|
title={Multi-task learning as a bargaining game},
|
|
author={Navon, Aviv and Shamsian, Aviv and Achituve, Idan and Maron, Haggai and Kawaguchi, Kenji and Chechik, Gal and Fetaya, Ethan},
|
|
journal={arXiv preprint arXiv:2202.01017},
|
|
year={2022}
|
|
}
|
|
@article{yu2020gradient,
|
|
title={Gradient surgery for multi-task learning},
|
|
author={Yu, Tianhe and Kumar, Saurabh and Gupta, Abhishek and Levine, Sergey and Hausman, Karol and Finn, Chelsea},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={33},
|
|
pages={5824--5836},
|
|
year={2020}
|
|
}
|
|
@article{renduchintala2023tied,
|
|
title={Tied-lora: Enhacing parameter efficiency of lora with weight tying},
|
|
author={Renduchintala, Adithya and Konuk, Tugrul and Kuchaiev, Oleksii},
|
|
journal={arXiv preprint arXiv:2311.09578},
|
|
year={2023}
|
|
}
|
|
@inproceedings{kwon2023efficient,
|
|
title={Efficient memory management for large language model serving with pagedattention},
|
|
author={Kwon, Woosuk and Li, Zhuohan and Zhuang, Siyuan and Sheng, Ying and Zheng, Lianmin and Yu, Cody Hao and Gonzalez, Joseph and Zhang, Hao and Stoica, Ion},
|
|
booktitle={Proceedings of the 29th Symposium on Operating Systems Principles},
|
|
pages={611--626},
|
|
year={2023}
|
|
}
|
|
|
|
@article{dai2024deepseekmoe,
|
|
title={Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models},
|
|
author={Dai, Damai and Deng, Chengqi and Zhao, Chenggang and Xu, RX and Gao, Huazuo and Chen, Deli and Li, Jiashi and Zeng, Wangding and Yu, Xingkai and Wu, Y and others},
|
|
journal={arXiv preprint arXiv:2401.06066},
|
|
year={2024}
|
|
}
|
|
@article{guo2025deepseek,
|
|
title={Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning},
|
|
author={Guo, Daya and Yang, Dejian and Zhang, Haowei and Song, Junxiao and Zhang, Ruoyu and Xu, Runxin and Zhu, Qihao and Ma, Shirong and Wang, Peiyi and Bi, Xiao and others},
|
|
journal={arXiv preprint arXiv:2501.12948},
|
|
year={2025}
|
|
}
|
|
@article{shazeer2017outrageously,
|
|
title={Outrageously large neural networks: The sparsely-gated mixture-of-experts layer},
|
|
author={Shazeer, Noam and Mirhoseini, Azalia and Maziarz, Krzysztof and Davis, Andy and Le, Quoc and Hinton, Geoffrey and Dean, Jeff},
|
|
journal={arXiv preprint arXiv:1701.06538},
|
|
year={2017}
|
|
}
|
|
@inproceedings{rajbhandari2022deepspeed,
|
|
title={Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale},
|
|
author={Rajbhandari, Samyam and Li, Conglong and Yao, Zhewei and Zhang, Minjia and Aminabadi, Reza Yazdani and Awan, Ammar Ahmad and Rasley, Jeff and He, Yuxiong},
|
|
booktitle={International conference on machine learning},
|
|
pages={18332--18346},
|
|
year={2022},
|
|
organization={PMLR}
|
|
}
|
|
@article{zhang2023instruction,
|
|
title={Instruction tuning for large language models: A survey},
|
|
author={Zhang, Shengyu and Dong, Linfeng and Li, Xiaoya and Zhang, Sen and Sun, Xiaofei and Wang, Shuhe and Li, Jiwei and Hu, Runyi and Zhang, Tianwei and Wu, Fei and others},
|
|
journal={arXiv preprint arXiv:2308.10792},
|
|
year={2023}
|
|
}
|
|
@article{pfeiffer2020adapterfusion,
|
|
title={Adapterfusion: Non-destructive task composition for transfer learning},
|
|
author={Pfeiffer, Jonas and Kamath, Aishwarya and R{\"u}ckl{\'e}, Andreas and Cho, Kyunghyun and Gurevych, Iryna},
|
|
journal={arXiv preprint arXiv:2005.00247},
|
|
year={2020}
|
|
}
|
|
@article{pfeiffer2020adapterhub,
|
|
title={Adapterhub: A framework for adapting transformers},
|
|
author={Pfeiffer, Jonas and R{\"u}ckl{\'e}, Andreas and Poth, Clifton and Kamath, Aishwarya and Vuli{\'c}, Ivan and Ruder, Sebastian and Cho, Kyunghyun and Gurevych, Iryna},
|
|
journal={arXiv preprint arXiv:2007.07779},
|
|
year={2020}
|
|
}
|
|
|
|
@article{lu2023uniadapter,
|
|
title={Uniadapter: Unified parameter-efficient transfer learning for cross-modal modeling},
|
|
author={Lu, Haoyu and Huo, Yuqi and Yang, Guoxing and Lu, Zhiwu and Zhan, Wei and Tomizuka, Masayoshi and Ding, Mingyu},
|
|
journal={arXiv preprint arXiv:2302.06605},
|
|
year={2023}
|
|
}
|
|
|
|
@article{fedus2022switch,
|
|
title={Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity},
|
|
author={Fedus, William and Zoph, Barret and Shazeer, Noam},
|
|
journal={Journal of Machine Learning Research},
|
|
volume={23},
|
|
number={120},
|
|
pages={1--39},
|
|
year={2022}
|
|
}
|
|
@article{lepikhin2020gshard,
|
|
title={Gshard: Scaling giant models with conditional computation and automatic sharding},
|
|
author={Lepikhin, Dmitry and Lee, HyoukJoong and Xu, Yuanzhong and Chen, Dehao and Firat, Orhan and Huang, Yanping and Krikun, Maxim and Shazeer, Noam and Chen, Zhifeng},
|
|
journal={arXiv preprint arXiv:2006.16668},
|
|
year={2020}
|
|
}
|
|
@article{luo2024moelora,
|
|
title={Moelora: Contrastive learning guided mixture of experts on parameter-efficient fine-tuning for large language models},
|
|
author={Luo, Tongxu and Lei, Jiahe and Lei, Fangyu and Liu, Weihao and He, Shizhu and Zhao, Jun and Liu, Kang},
|
|
journal={arXiv preprint arXiv:2402.12851},
|
|
year={2024}
|
|
}
|
|
@article{guo2024large,
|
|
title={Large language model based multi-agents: A survey of progress and challenges},
|
|
author={Guo, Taicheng and Chen, Xiuying and Wang, Yaqi and Chang, Ruidi and Pei, Shichao and Chawla, Nitesh V and Wiest, Olaf and Zhang, Xiangliang},
|
|
journal={arXiv preprint arXiv:2402.01680},
|
|
year={2024}
|
|
}
|
|
@article{zhao2023survey,
|
|
title={A survey of large language models},
|
|
author={Zhao, Wayne Xin and Zhou, Kun and Li, Junyi and Tang, Tianyi and Wang, Xiaolei and Hou, Yupeng and Min, Yingqian and Zhang, Beichen and Zhang, Junjie and Dong, Zican and others},
|
|
journal={arXiv preprint arXiv:2303.18223},
|
|
year={2023}
|
|
}
|
|
@article{gao2024higher,
|
|
title={Higher layers need more lora experts},
|
|
author={Gao, Chongyang and Chen, Kezhen and Rao, Jinmeng and Sun, Baochen and Liu, Ruibo and Peng, Daiyi and Zhang, Yawen and Guo, Xiaoyuan and Yang, Jie and Subrahmanian, VS},
|
|
journal={arXiv preprint arXiv:2402.08562},
|
|
year={2024}
|
|
}
|
|
@inproceedings{dou2024loramoe,
|
|
title={LoRAMoE: Alleviating world knowledge forgetting in large language models via MoE-style plugin},
|
|
author={Dou, Shihan and Zhou, Enyu and Liu, Yan and Gao, Songyang and Shen, Wei and Xiong, Limao and Zhou, Yuhao and Wang, Xiao and Xi, Zhiheng and Fan, Xiaoran and others},
|
|
booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
|
|
pages={1932--1945},
|
|
year={2024}
|
|
}
|
|
|
|
|
|
|
|
@article{achiam2023gpt,
|
|
title={Gpt-4 technical report},
|
|
author={Achiam, Josh and Adler, Steven and Agarwal, Sandhini and Ahmad, Lama and Akkaya, Ilge and Aleman, Florencia Leoni and Almeida, Diogo and Altenschmidt, Janko and Altman, Sam and Anadkat, Shyamal and others},
|
|
journal={arXiv preprint arXiv:2303.08774},
|
|
year={2023}
|
|
}
|
|
@article{jaszczur2021sparse,
|
|
title={Sparse is enough in scaling transformers},
|
|
author={Jaszczur, Sebastian and Chowdhery, Aakanksha and Mohiuddin, Afroz and Kaiser, Lukasz and Gajewski, Wojciech and Michalewski, Henryk and Kanerva, Jonni},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={34},
|
|
pages={9895--9907},
|
|
year={2021}
|
|
}
|
|
@inproceedings{standley2020tasks,
|
|
title={Which tasks should be learned together in multi-task learning?},
|
|
author={Standley, Trevor and Zamir, Amir and Chen, Dawn and Guibas, Leonidas and Malik, Jitendra and Savarese, Silvio},
|
|
booktitle={International conference on machine learning},
|
|
pages={9120--9132},
|
|
year={2020},
|
|
organization={PMLR}
|
|
}
|
|
@article{cai2024survey,
|
|
title={A survey on mixture of experts},
|
|
author={Cai, Weilin and Jiang, Juyong and Wang, Fan and Tang, Jing and Kim, Sunghun and Huang, Jiayi},
|
|
journal={arXiv preprint arXiv:2407.06204},
|
|
year={2024}
|
|
}
|
|
@article{karimi2021compacter,
|
|
title={Compacter: Efficient low-rank hypercomplex adapter layers},
|
|
author={Karimi Mahabadi, Rabeeh and Henderson, James and Ruder, Sebastian},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={34},
|
|
pages={1022--1035},
|
|
year={2021}
|
|
}
|
|
@article{bommasani2021opportunities,
|
|
title={On the opportunities and risks of foundation models},
|
|
author={Bommasani, Rishi and Hudson, Drew A and Adeli, Ehsan and Altman, Russ and Arora, Simran and von Arx, Sydney and Bernstein, Michael S and Bohg, Jeannette and Bosselut, Antoine and Brunskill, Emma and others},
|
|
journal={arXiv preprint arXiv:2108.07258},
|
|
year={2021}
|
|
}
|
|
@article{pan2024lisa,
|
|
title={LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning},
|
|
author={Pan, Rui and Liu, Xiang and Diao, Shizhe and Pi, Renjie and Zhang, Jipeng and Han, Chi and Zhang, Tong},
|
|
journal={arXiv preprint arXiv:2403.17919},
|
|
year={2024}
|
|
}
|
|
@article{feng2024mixture,
|
|
title={Mixture-of-loras: An efficient multitask tuning for large language models},
|
|
author={Feng, Wenfeng and Hao, Chuzhan and Zhang, Yuewei and Han, Yu and Wang, Hao},
|
|
journal={arXiv preprint arXiv:2403.03432},
|
|
year={2024}
|
|
}
|
|
@article{lester2021power,
|
|
title={The power of scale for parameter-efficient prompt tuning},
|
|
author={Lester, Brian and Al-Rfou, Rami and Constant, Noah},
|
|
journal={arXiv preprint arXiv:2104.08691},
|
|
year={2021}
|
|
}
|
|
@article{zhou2024lima,
|
|
title={Lima: Less is more for alignment},
|
|
author={Zhou, Chunting and Liu, Pengfei and Xu, Puxin and Iyer, Srinivasan and Sun, Jiao and Mao, Yuning and Ma, Xuezhe and Efrat, Avia and Yu, Ping and Yu, Lili and others},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={36},
|
|
year={2024}
|
|
}
|
|
@article{wei2021finetuned,
|
|
title={Finetuned language models are zero-shot learners},
|
|
author={Wei, Jason and Bosma, Maarten and Zhao, Vincent Y and Guu, Kelvin and Yu, Adams Wei and Lester, Brian and Du, Nan and Dai, Andrew M and Le, Quoc V},
|
|
journal={arXiv preprint arXiv:2109.01652},
|
|
year={2021}
|
|
}
|
|
|
|
@article{brynjolfsson2025generative,
|
|
title={Generative AI at work},
|
|
author={Brynjolfsson, Erik and Li, Danielle and Raymond, Lindsey},
|
|
journal={The Quarterly Journal of Economics},
|
|
pages={qjae044},
|
|
year={2025},
|
|
publisher={Oxford University Press}
|
|
}
|
|
@Misc{peft,
|
|
title = {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods},
|
|
author = {Sourab Mangrulkar and Sylvain Gugger and Lysandre Debut and Younes Belkada and Sayak Paul and Benjamin Bossan},
|
|
howpublished = {\url{https://github.com/huggingface/peft}},
|
|
year = {2022}
|
|
}
|
|
@article{li2023chatdoctor,
|
|
title={ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge},
|
|
author={Li, Yunxiang and Li, Zihan and Zhang, Kai and Dan, Ruilong and Jiang, Steve and Zhang, You},
|
|
journal={Cureus},
|
|
volume={15},
|
|
number={6},
|
|
year={2023},
|
|
publisher={Cureus}
|
|
}
|
|
@online{DatabricksBlog2023DollyV2,
|
|
author = {Mike Conover and Matt Hayes and Ankit Mathur and Jianwei Xie and Jun Wan and Sam Shah and Ali Ghodsi and Patrick Wendell and Matei Zaharia and Reynold Xin},
|
|
title = {Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM},
|
|
year = {2023},
|
|
url = {https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm},
|
|
urldate = {2023-06-30}
|
|
}
|
|
@inproceedings{nakano2021webgpt,
|
|
author = {Reiichiro Nakano and Jacob Hilton and Suchir Balaji and Jeff Wu and Long Ouyang and Christina Kim and Christopher Hesse and Shantanu Jain and Vineet Kosaraju and William Saunders and Xu Jiang and Karl Cobbe and Tyna Eloundou and Gretchen Krueger and Kevin Button and Matthew Knight and Benjamin Chess and John Schulman},
|
|
title = {WebGPT: Browser-assisted question-answering with human feedback},
|
|
booktitle = {arXiv},
|
|
year = 2021,
|
|
}
|
|
@inproceedings{zhang2023automatic,
|
|
title={Automatic Chain of Thought Prompting in Large Language Models},
|
|
author={Zhang, Zhuosheng and Zhang, Aston and Li, Mu and Smola, Alex},
|
|
booktitle={The Eleventh International Conference on Learning Representations (ICLR 2023)},
|
|
year={2023}
|
|
}
|
|
@misc{codealpaca,
|
|
author = {Sahil Chaudhary},
|
|
title = {Code Alpaca: An Instruction-following LLaMA model for code generation},
|
|
year = {2023},
|
|
publisher = {GitHub},
|
|
journal = {GitHub repository},
|
|
howpublished = {\url{https://github.com/sahil280114/codealpaca}},
|
|
}
|
|
@article{zhao2024hypermoe,
|
|
title={HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts},
|
|
author={Zhao, Hao and Qiu, Zihan and Wu, Huijia and Wang, Zili and He, Zhaofeng and Fu, Jie},
|
|
journal={arXiv preprint arXiv:2402.12656},
|
|
year={2024}
|
|
}
|
|
|
|
|
|
% Dataset
|
|
|
|
% Traffic State Prediction
|
|
|
|
|
|
@inproceedings{METR_LA/PEMS_BAY,
|
|
title={Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting},
|
|
author={Li, Yaguang and Yu, Rose and Shahabi, Cyrus and Liu, Yan},
|
|
booktitle={International Conference on Learning Representations},
|
|
year={2018}
|
|
}
|
|
|
|
@inproceedings{PEMSD3/7,
|
|
title={Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting},
|
|
author={Song, Chao and Lin, Youfang and Guo, Shengnan and Wan, Huaiyu},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={34},
|
|
number={01},
|
|
pages={914--921},
|
|
year={2020}
|
|
}
|
|
|
|
@inproceedings{PEMSD7M,
|
|
title={Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting},
|
|
author={Yu, Bing and Yin, Haoteng and Zhu, Zhanxing},
|
|
booktitle={Proceedings of the 27th International Joint Conference on Artificial Intelligence},
|
|
pages={3634--3640},
|
|
year={2018}
|
|
}
|
|
|
|
@inproceedings{PEMSD4/8,
|
|
title={Attention based spatial-temporal graph convolutional networks for traffic flow forecasting},
|
|
author={Guo, Shengnan and Lin, Youfang and Feng, Ning and Song, Chao and Wan, Huaiyu},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={33},
|
|
number={01},
|
|
pages={922--929},
|
|
year={2019}
|
|
}
|
|
|
|
@inproceedings{TaxiBJ,
|
|
title={Deep spatio-temporal residual networks for citywide crowd flows prediction},
|
|
author={Zhang, Junbo and Zheng, Yu and Qi, Dekang},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={31},
|
|
number={1},
|
|
year={2017}
|
|
}
|
|
|
|
@inproceedings{T-drive,
|
|
title={T-drive: driving directions based on taxi trajectories},
|
|
author={Yuan, Jing and Zheng, Yu and Zhang, Chengyang and Xie, Wenlei and Xie, Xing and Sun, Guangzhong and Huang, Yan},
|
|
booktitle={Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems},
|
|
pages={99--108},
|
|
year={2010}
|
|
}
|
|
|
|
@inproceedings{NYCTaxi/Bike,
|
|
title={Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction},
|
|
author={Yao, Huaxiu and Tang, Xianfeng and Wei, Hua and Zheng, Guanjie and Li, Zhenhui},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={33},
|
|
number={01},
|
|
pages={5668--5675},
|
|
year={2019}
|
|
}
|
|
|
|
@article{LargeST,
|
|
title={Largest: A benchmark dataset for large-scale traffic forecasting},
|
|
author={Liu, Xu and Xia, Yutong and Liang, Yuxuan and Hu, Junfeng and Wang, Yiwei and Bai, Lei and Huang, Chao and Liu, Zhenguang and Hooi, Bryan and Zimmermann, Roger},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={36},
|
|
pages={75354--75371},
|
|
year={2023}
|
|
}
|
|
|
|
% Trajectory Location Prediction
|
|
|
|
@article{Foursquare-NYC/TKY,
|
|
title={Participatory cultural mapping based on collective behavior data in location-based social networks},
|
|
author={Yang, Dingqi and Zhang, Daqing and Qu, Bingqing},
|
|
journal={ACM Transactions on Intelligent Systems and Technology},
|
|
volume={7},
|
|
number={3},
|
|
pages={1--23},
|
|
year={2016},
|
|
publisher={ACM New York, NY, USA}
|
|
}
|
|
|
|
@article{Porto,
|
|
title={VecCity: A taxonomy-guided library for map entity representation learning},
|
|
author={Zhang, Wentao and Wang, Jingyuan and Yang, Yifan and others},
|
|
journal={arXiv preprint arXiv:2411.00874},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{Gowalla/BrightKite,
|
|
title={Friendship and mobility: user movement in location-based social networks},
|
|
author={Cho, Eunjoon and Myers, Seth A and Leskovec, Jure},
|
|
booktitle={Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
|
|
pages={1082--1090},
|
|
year={2011}
|
|
}
|
|
|
|
@inproceedings{Instagram,
|
|
title={Content-aware hierarchical point-of-interest embedding model for successive POI recommendation},
|
|
author={Chang, Buru and Park, Yonggyu and Park, Donghyeon and Kim, Seongsoon and Kang, Jaewoo},
|
|
booktitle={Proceedings of the 27th International Joint Conference on Artificial Intelligence},
|
|
pages={3301--3307},
|
|
year={2018}
|
|
}
|
|
|
|
@inproceedings{Singapore,
|
|
title={Poi-enhancer: An llm-based semantic enhancement framework for poi representation learning},
|
|
author={Cheng, Jiawei and Wang, Jingyuan and Zhang, Yichuan and Ji, Jiahao and Zhu, Yuanshao and Zhang, Zhibo and Zhao, Xiangyu},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={39},
|
|
number={11},
|
|
pages={11509--11517},
|
|
year={2025}
|
|
}
|
|
|
|
% Travel Time Estimation
|
|
|
|
@inproceedings{Chengdu/DeepTTE,
|
|
title={When will you arrive? Estimating travel time based on deep neural networks},
|
|
author={Wang, Dong and Zhang, Junbo and Cao, Wei and Li, Jian and Zheng, Yu},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={32},
|
|
number={1},
|
|
year={2018}
|
|
}
|
|
|
|
@article{Beijing/TTPNet,
|
|
title={TTPNet: A neural network for travel time prediction based on tensor decomposition and graph embedding},
|
|
author={Shen, Yibin and Jin, Cheqing and Hua, Jiaxun and Huang, Dingjiang},
|
|
journal={IEEE Transactions on Knowledge and Data Engineering},
|
|
volume={34},
|
|
number={9},
|
|
pages={4514--4526},
|
|
year={2020},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
%Map Matching
|
|
|
|
@inproceedings{Global,
|
|
title={Dataset for testing and training of map-matching algorithms},
|
|
author={Kubi{\v{c}}ka, Mat{\v{e}}j and Cela, Arben and Moulin, Philippe and Mounier, Hugues and Niculescu, Silviu-Iulian},
|
|
booktitle={2015 IEEE Intelligent Vehicles Symposium},
|
|
pages={1088--1093},
|
|
year={2015},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@inproceedings{Seattle,
|
|
title={Hidden Markov map matching through noise and sparseness},
|
|
author={Newson, Paul and Krumm, John},
|
|
booktitle={Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},
|
|
pages={336--343},
|
|
year={2009}
|
|
}
|
|
|
|
% Model
|
|
|
|
Traffic State Prediction
|
|
|
|
@inproceedings{STSSDL,
|
|
title={How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning},
|
|
author={Gao, Haotian and Dong, Zheng and Yong, Jiawei and Fukushima, Shintaro and Taura, Kenjiro and Jiang, Renhe},
|
|
booktitle={The 39th Annual Conference on Neural Information Processing Systems},
|
|
year={2025}
|
|
}
|
|
|
|
@article{STAEformer,
|
|
title={Staeformer: Spatio-temporal adaptive embedding makes vanilla transformer SOTA for traffic forecasting},
|
|
author={Liu, Hangchen and Dong, Zheng and Jiang, Renhe and Deng, Jiewen and Deng, Jinliang and Chen, Quanjun and Song, Xuan},
|
|
journal={arXiv preprint arXiv:2308.10425},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{AutoSTF,
|
|
title={Autostf: Decoupled neural architecture search for cost-effective automated spatio-temporal forecasting},
|
|
author={Lyu, Tengfei and Zhang, Weijia and Deng, Jinliang and Liu, Hao},
|
|
booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1},
|
|
pages={985--996},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{STDMAE,
|
|
title={Spatial-temporal-decoupled masked pre-training for spatiotemporal forecasting},
|
|
author={Gao, Haotian and Jiang, Renhe and Dong, Zheng and Deng, Jinliang and Ma, Yuxin and Song, Xuan},
|
|
booktitle={Proceedings of the 33rd International Joint Conference on Artificial Intelligence},
|
|
pages={3998--4006},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{EAC,
|
|
title={Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting},
|
|
author={Chen, Wei and Liang, Yuxuan},
|
|
booktitle={The 13th International Conference on Learning Representations},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{GriddedTNP,
|
|
title={Gridded Transformer Neural Processes for Spatio-Temporal Data},
|
|
author={Ashman, Matthew and Diaconu, Cristiana and Langezaal, Eric and Weller, Adrian and Turner, Richard E},
|
|
booktitle={Proceedings of the 42nd International Conference on Machine Learning},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{PatchSTG,
|
|
title={Efficient large-scale traffic forecasting with transformers: A spatial data management perspective},
|
|
author={Fang, Yuchen and Liang, Yuxuan and Hui, Bo and Shao, Zezhi and Deng, Liwei and Liu, Xu and Jiang, Xinke and Zheng, Kai},
|
|
booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={307--317},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{SRSNet,
|
|
title={Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective},
|
|
author={Wu, Xingjian and Qiu, Xiangfei and Cheng, Hanyin and Li, Zhengyu and Hu, Jilin and Guo, Chenjuan and Yang, Bin},
|
|
booktitle={Proceedings of the 39th Annual Conference on Neural Information Processing Systems},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{FlashST,
|
|
title={FlashST: A simple and universal prompt-tuning framework for traffic prediction},
|
|
author={Li, Zhonghang and Xia, Lianghao and Xu, Yong and Huang, Chao},
|
|
booktitle={Proceedings of the 41st International Conference on Machine Learning},
|
|
pages={28978--28988},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{Convtimenet,
|
|
title={Convtimenet: A deep hierarchical fully convolutional model for multivariate time series analysis},
|
|
author={Cheng, Mingyue and Yang, Jiqian and Pan, Tingyue and Liu, Qi and Li, Zhi and Wang, Shijin},
|
|
booktitle={Companion Proceedings of the ACM on Web Conference 2025},
|
|
pages={171--180},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{Fredformer,
|
|
title={Fredformer: Frequency debiased transformer for time series forecasting},
|
|
author={Piao, Xihao and Chen, Zheng and Murayama, Taichi and Matsubara, Yasuko and Sakurai, Yasushi},
|
|
booktitle={Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining},
|
|
pages={2400--2410},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{Pathformer,
|
|
title={Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting},
|
|
author={Chen, Peng and ZHANG, Yingying and Cheng, Yunyao and Shu, Yang and Wang, Yihang and Wen, Qingsong and Yang, Bin and Guo, Chenjuan},
|
|
booktitle={The 12th International Conference on Learning Representations},
|
|
year={2024}
|
|
}
|
|
|
|
@article{HTVGNN,
|
|
title={A novel hybrid time-varying graph neural network for traffic flow forecasting},
|
|
author={Dai, Ben-Ao and Ye, Bao-Lin and Li, Lingxi},
|
|
journal={arXiv preprint arXiv:2401.10155},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{PatchTST,
|
|
title={A Time Series is Worth 64 Words: Long-term Forecasting with Transformers},
|
|
author={Nie, Yuqi and Nguyen, Nam H and Sinthong, Phanwadee and Kalagnanam, Jayant},
|
|
booktitle={The 11th International Conference on Learning Representations},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{DCST,
|
|
title={Make graph neural networks great again: a generic integration paradigm of topology-free patterns for traffic speed prediction},
|
|
author={Zhou, Yicheng and Wang, Pengfei and Dong, Hao and Zhang, Denghui and Yang, Dingqi and Fu, Yanjie and Wang, Pengyang},
|
|
booktitle={Proceedings of the 33rd International Joint Conference on Artificial Intelligence},
|
|
pages={2607--2615},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{STLLM,
|
|
title={Spatial-temporal large language model for traffic prediction},
|
|
author={Liu, Chenxi and Yang, Sun and Xu, Qianxiong and Li, Zhishuai and Long, Cheng and Li, Ziyue and Zhao, Rui},
|
|
booktitle={Proceedings of the 25th IEEE International Conference on Mobile Data Management},
|
|
pages={31--40},
|
|
year={2024},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@article{T-graphormer,
|
|
title={T-graphormer: Using transformers for spatiotemporal forecasting},
|
|
author={Bai, Hao Yuan and Liu, Xue},
|
|
journal={arXiv preprint arXiv:2501.13274},
|
|
year={2025}
|
|
}
|
|
|
|
@article{CKGGNN,
|
|
title={Context-aware knowledge graph framework for traffic speed forecasting using graph neural network},
|
|
author={Zhang, Yatao and Wang, Yi and Gao, Song and Raubal, Martin},
|
|
journal={IEEE Transactions on Intelligent Transportation Systems},
|
|
year={2024},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@inproceedings{EasyST,
|
|
title={EasyST: A Simple Framework for Spatio-Temporal Prediction},
|
|
author={Tang, Jiabin and Wei, Wei and Xia, Lianghao and Huang, Chao},
|
|
booktitle={Proceedings of the 33rd ACM International Conference on Information and Knowledge Management},
|
|
pages={2220--2229},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{LEAF,
|
|
title={Embracing large language models in traffic flow forecasting},
|
|
author={Zhao, Yusheng and Luo, Xiao and Wen, Haomin and Xiao, Zhiping and Ju, Wei and Zhang, Ming},
|
|
booktitle={Findings of the Association for Computational Linguistics: ACL 2025},
|
|
pages={8108--8123},
|
|
year={2025}
|
|
}
|
|
|
|
@article{MetaDG,
|
|
title={Meta Dynamic Graph for Traffic Flow Prediction},
|
|
author={Zou, Yiqing and Yuan, Hanning and Yang, Qianyu and Yuan, Ziqiang and Wang, Shuliang and Ruan, Sijie},
|
|
journal={arXiv preprint arXiv:2601.10328},
|
|
year={2026}
|
|
}
|
|
|
|
@inproceedings{TRACK,
|
|
title={Bridging traffic state and trajectory for dynamic road network and trajectory representation learning},
|
|
author={Han, Chengkai and Wang, Jingyuan and Wang, Yongyao and Yu, Xie and Lin, Hao and Li, Chao and Wu, Junjie},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={39},
|
|
number={11},
|
|
pages={11763--11771},
|
|
year={2025}
|
|
}
|
|
|
|
@article{HiMSNet,
|
|
title={Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data},
|
|
author={Xiong, Weijiang and Fonod, Robert and Alahi, Alexandre and Geroliminis, Nikolas},
|
|
journal={arXiv preprint arXiv:2501.03492},
|
|
year={2025}
|
|
}
|
|
|
|
@article{DST2former,
|
|
title={Dynamic trend fusion module for traffic flow prediction},
|
|
author={Chen, Jing and Ye, Haocheng and Ying, Zhian and Sun, Yuntao and Xu, Wenqiang},
|
|
journal={Applied Soft Computing},
|
|
volume={174},
|
|
pages={112979},
|
|
year={2025},
|
|
publisher={Elsevier}
|
|
}
|
|
|
|
@inproceedings{DSTMamba,
|
|
title={Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction},
|
|
author={He, Sicheng and Ji, Junzhong and Lei, Minglong},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={39},
|
|
number={11},
|
|
pages={11772--11780},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{ASeer,
|
|
title={Irregular traffic time series forecasting based on asynchronous spatio-temporal graph convolutional networks},
|
|
author={Zhang, Weijia and Zhang, Le and Han, Jindong and Liu, Hao and Fu, Yanjie and Zhou, Jingbo and Mei, Yu and Xiong, Hui},
|
|
booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={4302--4313},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{STHSepNet,
|
|
title={Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs},
|
|
author={Chen, Jiawen and Shao, Qi and Chen, Duxin and Yu, Wenwu},
|
|
booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={167--178},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{STWave,
|
|
title={When spatio-temporal meet wavelets: Disentangled traffic forecasting via efficient spectral graph attention networks},
|
|
author={Fang, Yuchen and Qin, Yanjun and Luo, Haiyong and Zhao, Fang and Xu, Bingbing and Zeng, Liang and Wang, Chenxing},
|
|
booktitle={Proceedings of the IEEE 39th International Conference on Data Engineering},
|
|
pages={517--529},
|
|
year={2023},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@inproceedings{HSTWAVE,
|
|
title={Riding the Wave: Multi-Scale Spatial-Temporal Graph Learning for Highway Traffic Flow Prediction Under Overload Scenarios},
|
|
author={Sun, Xigang and Jin, Jiahui and Wang, Hancheng and Sun, Xiangguo and Wang, Xiaoliang and Zhu, Jun},
|
|
booktitle={Proceedings of the 34th International Joint Conference on Artificial Intelligence},
|
|
pages={3317--3325},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{DSTAGNN,
|
|
title={Dstagnn: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting},
|
|
author={Lan, Shiyong and Ma, Yitong and Huang, Weikang and Wang, Wenwu and Yang, Hongyu and Li, Pyang},
|
|
booktitle={Proceedings of the 2022 International Conference on Machine Learning},
|
|
pages={11906--11917},
|
|
year={2022},
|
|
organization={PMLR}
|
|
}
|
|
|
|
@inproceedings{RSTIB,
|
|
title={Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting},
|
|
author={Chen, Min and Pang, Guansong and Wang, Wenjun and Yan, Cheng},
|
|
booktitle={Proceedings of the 42nd International Conference on Machine Learning},
|
|
year={2025}
|
|
}
|
|
|
|
@article{LSTTN,
|
|
title={LSTTN: A long-short term transformer-based spatiotemporal neural network for traffic flow forecasting},
|
|
author={Luo, Qinyao and He, Silu and Han, Xing and Wang, Yuhan and Li, Haifeng},
|
|
journal={Knowledge-Based Systems},
|
|
volume={293},
|
|
pages={111637},
|
|
year={2024},
|
|
publisher={Elsevier}
|
|
}
|
|
|
|
@inproceedings{LightST,
|
|
title={Efficient traffic prediction through spatio-temporal distillation},
|
|
author={Zhang, Qianru and Gao, Xinyi and Wang, Haixin and Yiu, Siu Ming and Yin, Hongzhi},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={39},
|
|
number={1},
|
|
pages={1093--1101},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{TimeMixer++,
|
|
title={TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis},
|
|
author={Wang, Shiyu and Li, Jiawei and Shi, Xiaoming and Ye, Zhou and Mo, Baichuan and Lin, Wenze and Shengtong, Ju and Chu, Zhixuan and Jin, Ming},
|
|
booktitle={Proceedings of the 13th International Conference on Learning Representations},
|
|
year={2025},
|
|
}
|
|
|
|
@article{BigST,
|
|
title={Bigst: Linear complexity spatio-temporal graph neural network for traffic forecasting on large-scale road networks},
|
|
author={Han, Jindong and Zhang, Weijia and Liu, Hao and Tao, Tao and Tan, Naiqiang and Xiong, Hui},
|
|
journal={Proceedings of the VLDB Endowment},
|
|
volume={17},
|
|
number={5},
|
|
pages={1081--1090},
|
|
year={2024},
|
|
publisher={VLDB Endowment}
|
|
}
|
|
|
|
@inproceedings{STID,
|
|
title={Spatial-temporal identity: A simple yet effective baseline for multivariate time series forecasting},
|
|
author={Shao, Zezhi and Zhang, Zhao and Wang, Fei and Wei, Wei and Xu, Yongjun},
|
|
booktitle={Proceedings of the 31st ACM International Conference on Information and Knowledge Management},
|
|
pages={4454--4458},
|
|
year={2022}
|
|
}
|
|
|
|
@inproceedings{UniST,
|
|
title={Unist: A prompt-empowered universal model for urban spatio-temporal prediction},
|
|
author={Yuan, Yuan and Ding, Jingtao and Feng, Jie and Jin, Depeng and Li, Yong},
|
|
booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={4095--4106},
|
|
year={2024}
|
|
}
|
|
|
|
%Trajectory Location Prediction
|
|
|
|
@inproceedings{DeepMove,
|
|
title={Deepmove: Predicting human mobility with attentional recurrent networks},
|
|
author={Feng, Jie and Li, Yong and Zhang, Chao and Sun, Funing and Meng, Fanchao and Guo, Ang and Jin, Depeng},
|
|
booktitle={Proceedings of the 2018 International Conference on World Wide Web},
|
|
pages={1459--1468},
|
|
year={2018}
|
|
}
|
|
|
|
@article{PLMTrajRec,
|
|
title={PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models},
|
|
author={Wei, Tonglong and Lin, Yan and Lin, Youfang and Guo, Shengnan and Hu, Jilin and Yuan, Haitao and Cong, Gao and Wan, Huaiyu},
|
|
journal={arXiv preprint arXiv:2410.14281},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{START,
|
|
title={Self-supervised trajectory representation learning with temporal regularities and travel semantics},
|
|
author={Jiang, Jiawei and Pan, Dayan and Ren, Houxing and Jiang, Xiaohan and Li, Chao and Wang, Jingyuan},
|
|
booktitle={Proceedings of the 39th International Conference on Data Engineering},
|
|
pages={843--855},
|
|
year={2023},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@article{LoTNext,
|
|
title={Taming the long tail in human mobility prediction},
|
|
author={Xu, Xiaohang and Jiang, Renhe and Yang, Chuang and Sezaki, Kaoru and others},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={37},
|
|
pages={54748--54771},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{RNTrajRec,
|
|
title={Rntrajrec: Road network enhanced trajectory recovery with spatial-temporal transformer},
|
|
author={Chen, Yuqi and Zhang, Hanyuan and Sun, Weiwei and Zheng, Baihua},
|
|
booktitle={Proceedings of the IEEE 39th International Conference on Data Engineering},
|
|
pages={829--842},
|
|
year={2023},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@inproceedings{CoMaPOI,
|
|
title={Comapoi: A collaborative multi-agent framework for next poi prediction bridging the gap between trajectory and language},
|
|
author={Zhong, Lin and Wang, Lingzhi and Yang, Xu and Liao, Qing},
|
|
booktitle={Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval},
|
|
pages={1768--1778},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{JGRM,
|
|
title={More than routing: Joint GPS and route modeling for refine trajectory representation learning},
|
|
author={Ma, Zhipeng and Tu, Zheyan and Chen, Xinhai and Zhang, Yan and Xia, Deguo and Zhou, Guyue and Chen, Yilun and Zheng, Yu and Gong, Jiangtao},
|
|
booktitle={Proceedings of the ACM Web Conference 2024},
|
|
pages={3064--3075},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{TrajSDE,
|
|
title={Improving transferability for cross-domain trajectory prediction via neural stochastic differential equation},
|
|
author={Park, Daehee and Jeong, Jaewoo and Yoon, Kuk-Jin},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={38},
|
|
number={9},
|
|
pages={10145--10154},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{DCHL,
|
|
title={Disentangled contrastive hypergraph learning for next POI recommendation},
|
|
author={Lai, Yantong and Su, Yijun and Wei, Lingwei and He, Tianqi and Wang, Haitao and Chen, Gaode and Zha, Daren and Liu, Qiang and Wang, Xingxing},
|
|
booktitle={Proceedings of the 47th international ACM SIGIR Conference on Research and Development in Information Retrieval},
|
|
pages={1452--1462},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{GNPRSID,
|
|
title={Generative next poi recommendation with semantic id},
|
|
author={Wang, Dongsheng and Huang, Yuxi and Gao, Shen and Wang, Yifan and Huang, Chengrui and Shang, Shuo},
|
|
booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={2904--2914},
|
|
year={2025}
|
|
}
|
|
|
|
@article{PLSPL,
|
|
title={Personalized long-and short-term preference learning for next POI recommendation},
|
|
author={Wu, Yuxia and Li, Ke and Zhao, Guoshuai and Qian, Xueming},
|
|
journal={IEEE Transactions on Knowledge and Data Engineering},
|
|
volume={34},
|
|
number={4},
|
|
pages={1944--1957},
|
|
year={2020},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@inproceedings{GETNEXT,
|
|
title={GETNext: Trajectory flow map enhanced transformer for next POI recommendation},
|
|
author={Yang, Song and Liu, Jiamou and Zhao, Kaiqi},
|
|
booktitle={Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval},
|
|
pages={1144--1153},
|
|
year={2022}
|
|
}
|
|
|
|
@article{CANOE,
|
|
title={Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Prediction},
|
|
author={Wu, Yuqian and Peng, Yuhong and Yu, Jiapeng and Liu, Xiangyu and Yan, Zeting and Lin, Kang and Su, Weifeng and Qu, Bingqing and Lee, Raymond and Yang, Dingqi},
|
|
journal={arXiv preprint arXiv:2509.11713},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{TPG,
|
|
title={Timestamps as prompts for geography-aware location recommendation},
|
|
author={Luo, Yan and Duan, Haoyi and Liu, Ye and Chung, Fu-Lai},
|
|
booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
|
|
pages={1697--1706},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{CLSPRec,
|
|
title={Clsprec: Contrastive learning of long and short-term preferences for next poi recommendation},
|
|
author={Duan, Chenghua and Fan, Wei and Zhou, Wei and Liu, Hu and Wen, Junhao},
|
|
booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
|
|
pages={473--482},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{AGRAN,
|
|
title={Adaptive graph representation learning for next POI recommendation},
|
|
author={Wang, Zhaobo and Zhu, Yanmin and Wang, Chunyang and Ma, Wenze and Li, Bo and Yu, Jiadi},
|
|
booktitle={Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
|
|
pages={393--402},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{LightPath,
|
|
title={Lightpath: Lightweight and scalable path representation learning},
|
|
author={Yang, Sean Bin and Hu, Jilin and Guo, Chenjuan and Yang, Bin and Jensen, Christian S},
|
|
booktitle={Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={2999--3010},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{ROTAN,
|
|
title={Rotan: A rotation-based temporal attention network for time-specific next poi recommendation},
|
|
author={Feng, Shanshan and Meng, Feiyu and Chen, Lisi and Shang, Shuo and Ong, Yew Soon},
|
|
booktitle={Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={759--770},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{FPMC,
|
|
title={Factorizing personalized markov chains for next-basket recommendation},
|
|
author={Rendle, Steffen and Freudenthaler, Christoph and Schmidt-Thieme, Lars},
|
|
booktitle={Proceedings of the 19th International Conference on World Wide Web},
|
|
pages={811--820},
|
|
year={2010}
|
|
}
|
|
|
|
@inproceedings{PRME,
|
|
author = {Shanshan Feng and
|
|
Xutao Li and
|
|
Yifeng Zeng and
|
|
Gao Cong and
|
|
Yeow Meng Chee and
|
|
Quan Yuan},
|
|
title = {Personalized Ranking Metric Embedding for Next New {POI} Recommendation},
|
|
booktitle = {Proceedings of the 24th International Joint Conference on Artificial Intelligence},
|
|
pages = {2069--2075},
|
|
publisher = {{AAAI} Press},
|
|
year = {2015},
|
|
url = {http://ijcai.org/Abstract/15/293},
|
|
timestamp = {Sun, 09 Nov 2025 09:23:03 +0100},
|
|
biburl = {https://dblp.org/rec/conf/ijcai/FengLZCCY15.bib},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org}
|
|
}
|
|
|
|
% Travel Time Estimation
|
|
|
|
@article{DOT,
|
|
title={Origin-destination travel time oracle for map-based services},
|
|
author={Lin, Yan and Wan, Huaiyu and Hu, Jilin and Guo, Shengnan and Yang, Bin and Lin, Youfang and Jensen, Christian S},
|
|
journal={Proceedings of the ACM on Management of Data},
|
|
volume={1},
|
|
number={3},
|
|
pages={1--27},
|
|
year={2023},
|
|
publisher={ACM New York, NY, USA}
|
|
}
|
|
|
|
@article{MetaTTE,
|
|
title={Fine-grained trajectory-based travel time estimation for multi-city scenarios based on deep meta-learning},
|
|
author={Wang, Chenxing and Zhao, Fang and Zhang, Haichao and Luo, Haiyong and Qin, Yanjun and Fang, Yuchen},
|
|
journal={IEEE Transactions on Intelligent Transportation Systems},
|
|
volume={23},
|
|
number={9},
|
|
pages={15716--15728},
|
|
year={2022},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@inproceedings{MVSTM,
|
|
title={Multi-view spatial-temporal model for travel time estimation},
|
|
author={Liu, Zichuan and Wu, Zhaoyang and Wang, Meng and Zhang, Rui},
|
|
booktitle={Proceedings of the 29th International Conference on Advances in Geographic Information Systems},
|
|
pages={646--649},
|
|
year={2021}
|
|
}
|
|
|
|
@inproceedings{DutyTTE,
|
|
title={DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation},
|
|
author={Mao, Xiaowei and Lin, Yan and Guo, Shengnan and Chen, Yubin and Xian, Xingyu and Wen, Haomin and Xu, Qisen and Lin, Youfang and Wan, Huaiyu},
|
|
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
|
volume={39},
|
|
number={12},
|
|
pages={12390--12398},
|
|
year={2025}
|
|
}
|
|
|
|
@article{TTPNet,
|
|
title={TTPNet: A neural network for travel time prediction based on tensor decomposition and graph embedding},
|
|
author={Shen, Yibin and Jin, Cheqing and Hua, Jiaxun and Huang, Dingjiang},
|
|
journal={IEEE Transactions on Knowledge and Data Engineering},
|
|
volume={34},
|
|
number={9},
|
|
pages={4514--4526},
|
|
year={2020},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@article{MTSTAN,
|
|
title={When will we arrive? A novel multi-task spatio-temporal attention network based on individual preference for estimating travel time},
|
|
author={Zou, Guojian and Lai, Ziliang and Ma, Changxi and Tu, Meiting and Fan, Jing and Li, Ye},
|
|
journal={IEEE Transactions on Intelligent Transportation Systems},
|
|
volume={24},
|
|
number={10},
|
|
pages={11438--11452},
|
|
year={2023},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@article{MulT-TTE,
|
|
title={Multi-faceted route representation learning for travel time estimation},
|
|
author={Liao, Tianxi and Han, Liangzhe and Xu, Yi and Zhu, Tongyu and Sun, Leilei and Du, Bowen},
|
|
journal={IEEE Transactions on Intelligent Transportation Systems},
|
|
volume={25},
|
|
number={9},
|
|
pages={11782--11793},
|
|
year={2024},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@article{MDTI,
|
|
title={Multimodal Trajectory Representation Learning for Travel Time Estimation},
|
|
author={Liu, Zhi and Hu, Xuyuan and Han, Xiao and Dai, Zhehao and Deng, Zhaolin and Shen, Guojiang and Kong, Xiangjie},
|
|
journal={arXiv preprint arXiv:2510.05840},
|
|
year={2025}
|
|
}
|
|
|
|
@article{ProbETA,
|
|
title={Link representation learning for probabilistic travel time estimation},
|
|
author={Xu, Chen and Wang, Qiang and Sun, Lijun},
|
|
journal={IEEE Transactions on Intelligent Transportation Systems},
|
|
year={2025},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
|
|
DeepTTE
|
|
|
|
|
|
@inproceedings{HierETA,
|
|
title={Interpreting trajectories from multiple views: A hierarchical self-attention network for estimating the time of arrival},
|
|
author={Chen, Zebin and Xiao, Xiaolin and Gong, Yue-Jiao and Fang, Jun and Ma, Nan and Chai, Hua and Cao, Zhiguang},
|
|
booktitle={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={2771--2779},
|
|
year={2022}
|
|
}
|
|
|
|
@inproceedings{HetETA,
|
|
title={HetETA: Heterogeneous information network embedding for estimating time of arrival},
|
|
author={Hong, Huiting and Lin, Yucheng and Yang, Xiaoqing and Li, Zang and Fu, Kung and Wang, Zheng and Qie, Xiaohu and Ye, Jieping},
|
|
booktitle={Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery \& data mining},
|
|
pages={2444--2454},
|
|
year={2020}
|
|
}
|
|
|
|
%Map Matching
|
|
|
|
@inproceedings{DeepMM,
|
|
title={DeepMM: Deep learning based map matching with data augmentation},
|
|
author={Zhao, Kai and Feng, Jie and Xu, Zhao and Xia, Tong and Chen, Lin and Sun, Funing and Guo, Diansheng and Jin, Depeng and Li, Yong},
|
|
booktitle={Proceedings of the 27th ACM SIGSPATIAL international conference on advances in geographic information systems},
|
|
pages={452--455},
|
|
year={2019}
|
|
}
|
|
|
|
@article{GraphMM,
|
|
title={Graphmm: Graph-based vehicular map matching by leveraging trajectory and road correlations},
|
|
author={Liu, Yu and Ge, Qian and Luo, Wei and Huang, Qiang and Zou, Lei and Wang, Haixu and Li, Xin and Liu, Chang},
|
|
journal={IEEE Transactions on Knowledge and Data Engineering},
|
|
volume={36},
|
|
number={1},
|
|
pages={184--198},
|
|
year={2023},
|
|
publisher={IEEE}
|
|
}
|
|
|
|
@article{DiffMM,
|
|
title={DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion},
|
|
author={Han, Chenxu and Yang, Sean Bin and Hu, Jilin},
|
|
journal={arXiv preprint arXiv:2601.08482},
|
|
year={2026}
|
|
}
|
|
|
|
@inproceedings{TRMMA,
|
|
title={Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching},
|
|
author={Tian, Wei and Shi, Jieming and Yiu, Man Lung},
|
|
booktitle={Proceedings of the IEEE 41st International Conference on Data Engineering (ICDE)},
|
|
pages={363--375},
|
|
year={2025},
|
|
organization={IEEE}
|
|
}
|
|
|
|
@article{L2MM,
|
|
title={L2MM: Learning to map matching with deep models for low-quality GPS trajectory data},
|
|
author={Jiang, Linli and Chen, Chao-Xiong and Chen, Chao},
|
|
journal={ACM Transactions on Knowledge Discovery from Data},
|
|
volume={17},
|
|
number={3},
|
|
pages={1--25},
|
|
year={2023},
|
|
publisher={ACM New York, NY}
|
|
}
|
|
|
|
@article{RLOMM,
|
|
title={RLOMM: An efficient and robust online map matching framework with reinforcement learning},
|
|
author={Chen, Minxiao and Yuan, Haitao and Jiang, Nan and Zheng, Zhihan and Wu, Sai and Zhou, Ao and Wang, Shangguang},
|
|
journal={Proceedings of the ACM on Management of Data},
|
|
volume={3},
|
|
number={3},
|
|
pages={1--26},
|
|
year={2025},
|
|
publisher={ACM New York, NY, USA}
|
|
}
|
|
|
|
@article{FMM,
|
|
title={Fast map matching, an algorithm integrating hidden Markov model with precomputation},
|
|
author={Can Yang and Gyozo Gidofalvi},
|
|
journal={International Journal of Geographical Information Science},
|
|
year={2018},
|
|
volume={32},
|
|
number={3},
|
|
pages={547 - 570}
|
|
}
|
|
|
|
% Roadmap Representation
|
|
@inproceedings{JCLRNT,
|
|
title={Jointly contrastive representation learning on road network and trajectory},
|
|
author={Mao, Zhenyu and Li, Ziyue and Li, Dedong and Bai, Lei and Zhao, Rui},
|
|
booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
|
|
pages={1501--1510},
|
|
year={2022}
|
|
}
|
|
|
|
@article{Garner,
|
|
title={Road network representation learning with the third law of geography},
|
|
author={Zhou, Haicang and Huang, Weiming and Chen, Yile and He, Tiantian and Cong, Gao and Ong, Yew Soon},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={37},
|
|
pages={11789--11813},
|
|
year={2024}
|
|
}
|
|
|
|
@inproceedings{SARN,
|
|
title={Spatial Structure-Aware Road Network Embedding via Graph Contrastive Learning.},
|
|
author={Chang, Yanchuan and Tanin, Egemen and Cao, Xin and Qi, Jianzhong},
|
|
booktitle={EDBT},
|
|
pages={144--156},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{HMMM,
|
|
author = {Paul Newson and
|
|
John Krumm},
|
|
editor = {Divyakant Agrawal and
|
|
Walid G. Aref and
|
|
Chang{-}Tien Lu and
|
|
Mohamed F. Mokbel and
|
|
Peter Scheuermann and
|
|
Cyrus Shahabi and
|
|
Ouri Wolfson},
|
|
title = {Hidden Markov map matching through noise and sparseness},
|
|
booktitle = {Proceedings of the 17th ACM International Symposium on Advances in Geographic
|
|
Information Systems},
|
|
pages = {336--343},
|
|
year = {2009},
|
|
publisher = {{ACM}}
|
|
}
|
|
|
|
@inproceedings{STMatching,
|
|
author = {Yin Lou and
|
|
Chengyang Zhang and
|
|
Yu Zheng and
|
|
Xing Xie and
|
|
Wei Wang and
|
|
Yan Huang},
|
|
editor = {Divyakant Agrawal and
|
|
Walid G. Aref and
|
|
Chang{-}Tien Lu and
|
|
Mohamed F. Mokbel and
|
|
Peter Scheuermann and
|
|
Cyrus Shahabi and
|
|
Ouri Wolfson},
|
|
title = {Map-matching for low-sampling-rate {GPS} trajectories},
|
|
booktitle = {Proceedings of the 17th ACM International Symposium on Advances in Geographic
|
|
Information Systems},
|
|
pages = {352--361},
|
|
publisher = {{ACM}},
|
|
year = {2009}
|
|
}
|
|
|
|
|
|
% Related Works
|
|
|
|
|
|
% ST Benchmark
|
|
|
|
% Traditional Models
|
|
|
|
@inproceedings{Libcity,
|
|
title={Libcity: An open library for traffic prediction},
|
|
author={Wang, Jingyuan and Jiang, Jiawei and Jiang, Wenjun and Li, Chao and Zhao, Wayne Xin},
|
|
booktitle={Proceedings of the 29th international conference on advances in geographic information systems},
|
|
pages={145--148},
|
|
year={2021}
|
|
}
|
|
VecCity(引过了)
|
|
LargeST(引过了)
|
|
|
|
@inproceedings{Dl-traff,
|
|
title={Dl-traff: Survey and benchmark of deep learning models for urban traffic prediction},
|
|
author={Jiang, Renhe and Yin, Du and Wang, Zhaonan and Wang, Yizhuo and Deng, Jiewen and Liu, Hangchen and Cai, Zekun and Deng, Jinliang and Song, Xuan and Shibasaki, Ryosuke},
|
|
booktitle={Proceedings of the 30th ACM international conference on information \& knowledge management},
|
|
pages={4515--4525},
|
|
year={2021}
|
|
}
|
|
|
|
@article{Torchspatial,
|
|
title={Torchspatial: A location encoding framework and benchmark for spatial representation learning},
|
|
author={Wu, Nemin and Cao, Qian and Wang, Zhangyu and Liu, Zeping and Qi, Yanlin and Zhang, Jielu and Ni, Joshua and Yao, Xiaobai and Ma, Hongxu and Mu, Lan and others},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={37},
|
|
pages={81437--81460},
|
|
year={2024}
|
|
}
|
|
|
|
@article{DGCRN,
|
|
title={Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution},
|
|
author={Li, Fuxian and Feng, Jie and Yan, Huan and Jin, Guangyin and Yang, Fan and Sun, Funing and Jin, Depeng and Li, Yong},
|
|
journal={ACM Transactions on Knowledge Discovery from Data},
|
|
volume={17},
|
|
number={1},
|
|
pages={1--21},
|
|
year={2023},
|
|
publisher={ACM New York, NY}
|
|
}
|
|
|
|
% Foundation Models
|
|
|
|
@inproceedings{CityBench,
|
|
title={Citybench: Evaluating the capabilities of large language models for urban tasks},
|
|
author={Feng, Jie and Zhang, Jun and Liu, Tianhui and Zhang, Xin and Ouyang, Tianjian and Yan, Junbo and Du, Yuwei and Guo, Siqi and Li, Yong},
|
|
booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
|
|
pages={5413--5424},
|
|
year={2025}
|
|
}
|
|
|
|
@article{USTBench,
|
|
title={USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents},
|
|
author={Lai, Siqi and Ning, Yansong and Yuan, Zirui and Chen, Zhixi and Liu, Hao},
|
|
journal={arXiv preprint arXiv:2505.17572},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{STBench,
|
|
title={Stbench: Assessing the ability of large language models in spatio-temporal analysis},
|
|
author={Li, Wenbin and Yao, Di and Zhao, Ruibo and Chen, Wenjie and Xu, Zijie and Luo, Chengxue and Gong, Chang and Jing, Quanliang and Tan, Haining and Bi, Jingping},
|
|
booktitle={Companion Proceedings of the ACM Web Conference 2025},
|
|
pages={749--752},
|
|
year={2025}
|
|
}
|
|
|
|
% LLM Agents
|
|
|
|
%Code Agent
|
|
|
|
@article{Swe-agent,
|
|
title={Swe-agent: Agent-computer interfaces enable automated software engineering},
|
|
author={Yang, John and Jimenez, Carlos E and Wettig, Alexander and Lieret, Kilian and Yao, Shunyu and Narasimhan, Karthik and Press, Ofir},
|
|
journal={Advances in Neural Information Processing Systems},
|
|
volume={37},
|
|
pages={50528--50652},
|
|
year={2024}
|
|
}
|
|
|
|
@article{Live-SWE-agent,
|
|
author = {Xia, Chunqiu Steven and Wang, Zhe and Yang, Yan and Wei, Yuxiang and Zhang, Lingming},
|
|
title = {Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?},
|
|
year = {2025},
|
|
journal = {arXiv preprint},
|
|
}
|
|
|
|
@inproceedings{OpenHands,
|
|
title={OpenHands: An Open Platform for AI Software Developers as Generalist Agents},
|
|
author={Wang, Xingyao and Li, Boxuan and Song, Yufan and Xu, Frank F and Tang, Xiangru and Zhuge, Mingchen and Pan, Jiayi and Song, Yueqi and Li, Bowen and Singh, Jaskirat and others},
|
|
booktitle={Proceedings of the 13th International Conference on Learning Representations},
|
|
year={2025}
|
|
}
|
|
|
|
% Paper Reporduce Agent
|
|
|
|
% Paper to Code Agent
|
|
|
|
@misc{DeepCode,
|
|
title={DeepCode: Open Agentic Coding},
|
|
author={Zongwei Li and Zhonghang Li and Zirui Guo and Xubin Ren and Chao Huang},
|
|
year={2025},
|
|
eprint={2512.07921},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.SE},
|
|
url={https://arxiv.org/abs/2512.07921},
|
|
}
|
|
|
|
@article{Paper2code,
|
|
title={Paper2code: Automating code generation from scientific papers in machine learning},
|
|
author={Seo, Minju and Baek, Jinheon and Lee, Seongyun and Hwang, Sung Ju},
|
|
journal={arXiv preprint arXiv:2504.17192},
|
|
year={2025}
|
|
}
|
|
|
|
% Auto Reproduce Agent
|
|
|
|
@article{Agentlaboratory,
|
|
title={Agent laboratory: Using llm agents as research assistants},
|
|
author={Schmidgall, Samuel and Su, Yusheng and Wang, Ze and Sun, Ximeng and Wu, Jialian and Yu, Xiaodong and Liu, Jiang and Moor, Michael and Liu, Zicheng and Barsoum, Emad},
|
|
journal={Findings of the Association for Computational Linguistics: EMNLP 2025},
|
|
pages={5977--6043},
|
|
year={2025},
|
|
publisher={Association for Computational Linguistics}
|
|
}
|
|
|
|
@article{Autoreproduce,
|
|
title={Autoreproduce: Automatic ai experiment reproduction with paper lineage},
|
|
author={Zhao, Xuanle and Sang, Zilin and Li, Yuxuan and Shi, Qi and Zhao, Weilun and Wang, Shuo and Zhang, Duzhen and Han, Xu and Liu, Zhiyuan and Sun, Maosong},
|
|
journal={arXiv preprint arXiv:2505.20662},
|
|
year={2025}
|
|
}
|
|
|
|
% Machine Learning Engineering Agent
|
|
|
|
@article{ML-Master,
|
|
title={ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning},
|
|
author={Liu, Zexi and Cai, Yuzhu and Zhu, Xinyu and Zheng, Yujie and Chen, Runkun and Wen, Ying and Wang, Yanfeng and Chen, Siheng and others},
|
|
journal={arXiv preprint arXiv:2506.16499},
|
|
year={2025}
|
|
}
|
|
|
|
@inproceedings{PiML,
|
|
title={PiML: Automated Machine Learning Workflow Optimization using LLM Agents},
|
|
author={Chopde, Abhishek and Pettiwala, Fardeen and Kirubananth, Sankar and Botla, Sai Kiran and Kethan, Pachipulusu Ayyappa},
|
|
booktitle={AutoML 2025 Methods Track},
|
|
year={2025}
|
|
} |