10 papers
Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
Zixuan Ren, Jinliang Lu, Junhong Wu +5
Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research…
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Jingcheng Deng, Zihao Wei, Liang Pang +4
Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reason…
LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
Jianghao Chen, Junhong Wu, Yangyifan Xu +1
Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip…
Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
Wen Yang, Junhong Wu, Chong Li +2
Recent advancements in Reinforcement Post-Training (RPT) have significantly enhanced the capabilities of Large Reasoning Models (LRMs), sparking increased interest in the generaliz…
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
Haozhe Wang, Qixin Xu, Che Liu +3
Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success…
Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Pu Jian, Junhong Wu, Wei Sun +3
Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\te…