6 papers
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
Yuhang Zhou, Jing Zhu, Shengyi Qian +7
Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Op…
CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning
Ming Li, Chenguang Wang, Yijun Liang +6
Recent agentic Multi-Modal Large Language Models (MLLMs) such as GPT-o3 have achieved near-ceiling scores on various existing benchmarks, motivating a demand for more challenging t…
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Xiyao Wang, Zhengyuan Yang, Chao Feng +10
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasonin…
What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
Ming Li, Zhengyuan Yang, Xiyao Wang +4
Large reasoning models (LRMs) achieve strong reasoning performance by emitting long chains of thought. Yet, these verbose traces slow down inference and often drift into unnecessar…
Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications
Yuhang Zhou, Paiheng Xu, Xiyao Wang +3
Emojis, which encapsulate semantics beyond mere words or phrases, have become prevalent in social network communications. This has spurred increasing scholarly interest in explorin…
Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
Yuhang Zhou, Jing Zhu, Paiheng Xu +5
Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD…