Siqi Fan

19 papers A* 5Journal 12Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
CoThink: Token-Efficient Reasoning via Instruct Models Guiding Reasoning Models.
CoRR
Siqi Fan, Peng Han, Shuo Shang, Yequan Wang, Aixin Sun
2025 J jnl
Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History.
CoRR
Qishuai Zhong, Zongmin Li, Siqi Fan, Aixin Sun
2025 — conf
Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement.
ACL (1)
Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu
2025 J jnl
Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement.
CoRR
Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu
2025 J jnl
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs.
CoRR
Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang, Kang Liu, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang
2025 A* conf
Not All Layers of LLMs Are Necessary During Inference.
IJCAI
Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang
2025 J jnl
Position-Aware Depth Decay Decoding (D
CoRR
Siqi Fan, Xuezhi Fang, Xingrun Xing, Peng Han, Shuo Shang, Yequan Wang
2025 — conf
Position-Aware Depth Decay Decoding (D³): Boosting Large Language Model Inference Efficiency.
ACL (Findings)
Siqi Fan, Xuezhi Fang, Xingrun Xing, Peng Han, Shuo Shang, Yequan Wang
2024 A* conf
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging.
EMNLP
Yiming Ju, Ziyi Ni, Xingrun Xing, Zhixiong Zeng, Hanyu Zhao, Siqi Fan, Zheng Zhang
2024 J jnl
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging.
CoRR
Yiming Ju, Ziyi Ni, Xingrun Xing, Zhixiong Zeng, Hanyu Zhao, Siqi Fan, Zheng Zhang
2024 J jnl
Not all Layers of LLMs are Necessary during Inference.
CoRR
Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang, Zhongyuan Wang
2024 A* conf
SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms.
ICML
Xingrun Xing, Zheng Zhang, Ziyi Ni, Shitao Xiao, Yiming Ju, Siqi Fan, Yequan Wang, Jiajun Zhang, Guoqi Li
2024 J jnl
SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms.
CoRR
Xingrun Xing, Zheng Zhang, Ziyi Ni, Shitao Xiao, Yiming Ju, Siqi Fan, Yequan Wang, Jiajun Zhang, Guoqi Li
2023 A* conf
EmpMFF: A Multi-factor Sequence Fusion Framework for Empathetic Response Generation.
WWW
Xiaobing Pang, Yequan Wang, Siqi Fan, Lisi Chen, Shuo Shang, Peng Han
2023 J jnl
FLM-101B: An Open LLM and How to Train It with $100K Budget.
CoRR
Xiang Li, Yiqun Yao, Xin Jiang, Xuezhi Fang, Xuying Meng, Siqi Fan, Peng Han, Jing Li, Li Du, Bowen Qin, Zheng Zhang, Aixin Sun, Yequan Wang
2023 J jnl
UaMC: user-augmented conversation recommendation via multi-modal graph learning and context mining.
World Wide Web (WWW)
Siqi Fan, Yequan Wang, Xiaobing Pang, Lisi Chen, Peng Han, Shuo Shang
2022 A* conf
Interactive Information Extraction by Semantic Information Graph.
IJCAI
Siqi Fan, Yequan Wang, Jing Li, Zheng Zhang, Shuo Shang, Peng Han
2021 J jnl
Few-Shot Relation Extraction Towards Special Interests.
Big Data Res.
Siqi Fan, Binbin Zhang, Silin Zhou, Menghan Wang, Ke Li
2021 J jnl
Route Search and Planning: A Survey.
Big Data Res.
Ke Li, Xuan Rao, Xiaobing Pang, Lisi Chen, Siqi Fan