Xiaohui Li
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
arXiv 2026
Accelerating Masked Image Generation by Learning Latent Controlled Dynamics
arXiv 2026
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
arXiv 2026
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
arXiv 2025
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
arXiv 2025
EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation
arXiv 2025
The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs
arXiv 2025
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
CVPR 2025 1
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers