Xiyang Wu
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
arXiv 2026
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
arXiv 2026
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
arXiv 2026
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
arXiv 2025
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
arXiv 2025
First Frame Is the Place to Go for Video Content Customization
arXiv 2025
A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
arXiv 2025
AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
arXiv 2024
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
CVPR 2024 1
iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers