Xiangyang Zhu

Venues

Frequent coauthors

Papers

1. MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine
   AAAI 2026 ·

   Kaiyuan Ji

   DBLP profile ↗ORCID search ↗
2. One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework
   ACL 2026 ·

   Qi Jia

   DBLP profile ↗ORCID search ↗
3. SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models
   AAAI 2026 ·

   Hanqing Wang

   DBLP profile ↗ORCID search ↗
4. VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
   AAAI 2026 ·

   Linhan Cao

   DBLP profile ↗ORCID search ↗
5. Efficient Face Image Quality Assessment via Self-Training and Knowledge Distillation
   ICCV 2025 ·

   Wei Sun

   DBLP profile ↗ORCID search ↗
6. Lumina-Image 2.0: a Unified and Efficient Image Generative Framework
   ICCV 2025 ·

   Qi Qin

   DBLP profile ↗ORCID search ↗
7. Semantics Versus Identity: A Divide-and-Conquer Approach Towards Adjustable Medical Image De-Identification
   ICCV 2025 ·

   Yuan Tian

   DBLP profile ↗ORCID search ↗
8. VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results
   ICCV 2025 ·

   Sizhuo Ma

   DBLP profile ↗ORCID search ↗
9. VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
   ICCV 2025 ·

   Hanwei Zhu

   DBLP profile ↗ORCID search ↗
10. Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
    NeurIPS 2024 ·

    Le Zhuo

    DBLP profile ↗ORCID search ↗
11. No Time to Train: Empowering Non-Parametric Networks for Few-Shot 3D Scene Segmentation
    CVPR 2024 · Xiangyang Zhu