collaborators

10 papers

cs.CL2026

Scaling Native Multimodal Pre-Training From Scratch

Haoyuan Wu, Aoqi Wu, Hai Wang +3

Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of the multimodal physical world.…

cs.CL2026

Diversity or Precision? A Deep Dive into Next Token Prediction

Haoyuan Wu, Hai Wang, Jiajia Wu +5

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL trai…

cs.CL2026

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient

Rui Ming, Haoyuan Wu, Shoubo Hu +2

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL)…

cs.CL2025

ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving

Haoyuan Wu, Xueyi Chen, Rui Ming +4

Large language models (LLMs) demonstrate significant reasoning capabilities, particularly through long chain-of-thought (CoT) processes, which can be elicited by reinforcement lear…

cs.CL2025

On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding

Haoyuan Wu, Rui Ming, Jilong Gao +6

Large language models (LLMs) achieve remarkable performance in code generation tasks. However, a significant performance disparity persists between popular programming languages (e…

cs.CL2025

Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

Haoyuan Wu, Haoxing Chen, Xiaodong Chen +10

The Mixture of Experts (MoE) architecture is a cornerstone of modern state-of-the-art (SOTA) large language models (LLMs). MoE models facilitate scalability by enabling sparse para…