6 papers
K2-Think: A Parameter-Efficient Reasoning System
Zhoujun Cheng, Richard Fan, Shibo Hao +28
K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1.…
Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
Hanlin Zhu, Shibo Hao, Zhiting Hu +3
Previous work shows that the chain of continuous thought (continuous CoT) improves the reasoning capability of large language models (LLMs) by enabling implicit parallel thinking,…
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Zhoujun Cheng, Shibo Hao, Tianyang Liu +21
Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our…
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
Yanbin Yin, Kun Zhou, Zhen Wang +11
The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard prac…
Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
Hanlin Zhu, Shibo Hao, Zhiting Hu +3
Large Language Models (LLMs) have demonstrated remarkable performance in many applications, including challenging reasoning problems via chain-of-thoughts (CoTs) techniques that ge…
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
Somanshu Singla, Zhen Wang, Tianyang Liu +3
Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to…