| Not all layers of llms are necessary during inference S Fan, X Jiang, X Li, X Meng, P Han, S Shang, A Sun, Y Wang, Z Wang IJCAI 2025, 2024 | 81 | 2024 |
| Flm-101b: An open llm and how to train it with $100 k budget X Li, Y Yao, X Jiang, X Fang, X Meng, S Fan, P Han, J Li, L Du, B Qin, ... arXiv preprint arXiv:2309.03852, 2023 | 39 | 2023 |
| Spikelm: Towards general spike-driven language modeling via elastic bi-spiking mechanisms X Xing, Z Zhang, Z Ni, S Xiao, Y Ju, S Fan, Y Wang, J Zhang, G Li ICML 2024, 2024 | 31 | 2024 |
| Route search and planning: A survey K Li, X Rao, XB Pang, L Chen, S Fan Big data research 26, 100246, 2021 | 30 | 2021 |
| Empmff: A multi-factor sequence fusion framework for empathetic response generation X Pang, Y Wang, S Fan, L Chen, S Shang, P Han Proceedings of the ACM web conference 2023, 1754-1764, 2023 | 12 | 2023 |
| Interactive Information Extraction by Semantic Information Graph. S Fan, Y Wang, J Li, Z Zhang, S Shang, P Han IJCAI, 4100-4106, 2022 | 8 | 2022 |
| Cothink: Token-efficient reasoning via instruct models guiding reasoning models S Fan, P Han, S Shang, Y Wang, A Sun arXiv preprint arXiv:2505.22017, 2025 | 7 | 2025 |
| Uamc: user-augmented conversation recommendation via multi-modal graph learning and context mining S Fan, Y Wang, X Pang, L Chen, P Han, S Shang World Wide Web 26 (6), 4109-4129, 2023 | 7 | 2023 |
| If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs S Fan, X Huang, Y Yao, X Fang, K Liu, P Han, S Shang, A Sun, Y Wang arXiv preprint arXiv:2503.23514, 2025 | 6 | 2025 |
| Few-shot relation extraction towards special interests S Fan, B Zhang, S Zhou, M Wang, K Li Big Data Research 26, 100273, 2021 | 6 | 2021 |
| Mitigating training imbalance in llm fine-tuning via selective parameter merging Y Ju, Z Ni, X Xing, Z Zeng, S Fan, Z Zhang EMNLP 2024, 2024 | 4 | 2024 |
| Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History Q Zhong, Z Li, S Fan, A Sun arXiv preprint arXiv:2505.21362, 2025 | 2 | 2025 |
| Position-Aware Depth Decay Decoding (): Boosting Large Language Model Inference Efficiency S Fan, X Fang, X Xing, P Han, S Shang, Y Wang ACL 2025 (Findings), 2025 | 1 | 2025 |
| The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models S Fan, B Qin, P Han, S Shang, Y Wang, A Sun | 1 | 2025 |
| Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement X Yuan, Z Yang, Z Huang, Y Wang, S Fan, Y Ju, J Zhao, K Liu Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | | 2025 |
| Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement X Yuan, Z Yang, Z Huang, Y Wang, S Fan, Y Ju, J Zhao, K Liu ACL 2025, 2025 | | 2025 |
| NanoLM: an Affordable LLM Study Benchmark via Accurate Loss Prediction across Scales YW Yiqun Yao, Siqi Fan, Xiusheng Huang, Xuezhi Fang, Xiang Li, Ziyi Ni, Xin ... SCI-FM @ ICLR 2025, 2025 | | 2025 |
Yequan Wang 王业全Beijing Academy of Artificial IntelligenceVerified email at mails.tsinghua.edu.cn
