Xiaoye Qu

Spotlight on Token Perception for Multimodal Reinforcement Learning

ExGRPO: Learning to Reason from Experience

FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting

Diversity-Incentivized Exploration for Versatile Reasoning

Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning

Flash-DMD: Unifying Distillation and Refinement for High-Fidelity Few-Step Image Generation

Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Learning to Reason under Off-Policy Guidance

Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

LASP-2: Rethinking Sequence Parallelism for Linear Attention and its Hybrid

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

Does Your Video-language Model Actually Understand the Language Input?

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Demystifying the Underappreciated Long-Tail Problems in Large Vision Language Models

Strategy-centric Synthesis: Connecting Billions of Image-Text Pairs to High-Quality Visual Instruction Data

Are Large Vision-Language Models Robust to Adversarial Visual Transformations?