420 citations · 572 across the 28 of their papers we have counts for
10 papers · 1 filter
Lost at the Beginning of Reasoning
Baohao Liao, Xinyi Chen, Sara Rajaee +5
Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that…
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Zhiyuan Hu, Yibo Wang, Hanze Dong +5
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can inciden…
Scalable Chain of Thoughts via Elastic Reasoning
Yuhui Xu, Hanze Dong, Lei Wang +3
Large reasoning models (LRMs) have achieved remarkable progress on complex tasks by generating extended chains of thought (CoT). However, their uncontrolled output lengths pose sig…
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
Tianbao Xie, Jiaqi Deng, Xiaochuan Li +12
Graphical user interface (GUI) grounding, the ability to map natural language instructions to specific actions on graphical user interfaces, remains a critical bottleneck in comput…
Fractured Chain-of-Thought Reasoning
Baohao Liao, Hanze Dong, Yuhui Xu +4
Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference…
Entropy-Based Block Pruning for Efficient Large Language Models
Liangwei Yang, Yuhui Xu, Juntao Tan +5
As large language models continue to scale, their growing computational and storage demands pose significant challenges for real-world deployment. In this work, we investigate redu…
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
Wei Xiong, Jiarui Yao, Yuhui Xu +8
Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its…
Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling
Heng Chang, Liang Gu, Cheng Hu +5
Cross-domain recommendation (CDR) is a task that aims to improve the recommendation performance in a target domain by leveraging the information from source domains. Contrastive le…
Reward Models Identify Consistency, Not Causality
Yuhui Xu, Hanze Dong, Lei Wang +2
Reward models (RMs) play a crucial role in aligning large language models (LLMs) with human preferences and enhancing reasoning quality. Traditionally, RMs are trained to rank cand…
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Baohao Liao, Yuhui Xu, Hanze Dong +5
We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combine…