5 papers
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Yuming Yang, Mingyoung Lai, Wanxu Zhao +13
Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show t…
Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
Zhihao Zhang, Qiaole Dong, Qi Zhang +12
Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. W…
DE-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks
Jianing He, Qi Zhang, Weiping Ding +4
Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. Howe…
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Mingqi Wu, Zhihao Zhang, Qiaole Dong +11
Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield subst…
Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
Jingqi Tong, Jixin Tang, Hangcheng Li +21
Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underex…