Xingwei Qu

YuE: Scaling Open Foundation Models for Long-Form Music Generation

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

First return, entropy-eliciting explore

COIG-Writer: A High-Quality Chinese Creative Writing with Thought Process Dataset

KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks

MuPT: A Generative Symbolic Music Pretrained Transformer

LIME: LESS IS MORE FOR MLLM EVALUATION

OmniBench: Towards The Future of Universal Omni-Language Models

Can MLLMs Understand the Deep Implication Behind Chinese Images?