Zhaopeng Tu

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

Castle-in-the-Air: Evaluating MLLM Visual Abilities on Human Cognitive Benchmarks

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

The Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

RaSA: Rank-Sharing Low-Rank Adaptation

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Competing Large Language Models in Multi-Agent Gaming Environments

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Insight Over Sight? Exploring the Vision-Knowledge Conflicts in Multimodal LLMs