Xiangyang Zhu
13 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (32) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad
🌈
Renaissance Researcher
(5)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(66)
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(8)
Computer Vision
(6)
Deep Learning
(5)
Machine Learning
(5)
Application Areas
(3)
Learning Paradigms
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Analysis
(2)
Generation
(2)
Models
(2)
Processing
(2)
Healthcare & Medicine
(1)
Natural Language Processing
(1)
Keywords
few-shot learning
(3)
video quality assessment
(2)
multimodal large language model
(2)
text-to-image generation
(2)
multimodal learning
(2)
diffusion transformer
(2)
image generation
(1)
image captioning
(1)
zero-shot learning
(1)
chain-of-thought reasoning
(1)
object detection
(1)
benchmark evaluation
(1)
privacy preservation
(1)
domain adaptation
(1)
neural network optimization
(1)
instruction following
(1)
out-of-distribution generalization
(1)
instruction tuning
(1)
scene segmentation
(1)
transfer learning
(1)
Papers
A3: Towards Advertising Aesthetic Assessment
CVPR 2026
Generalizable Video Quality Assessment via Weak-to-Strong Learning
CVPR 2026
MedOmni-45°: A Safety–Performance Benchmark for Reasoning-Oriented LLMs in Medicine
AAAI 2026
One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework
ACL 2026
SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models
AAAI 2026
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
AAAI 2026
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
ICCV 2025
Semantic versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
ICCV 2025
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
NeurIPS 2024
No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
CVPR 2024
Efficient Multi-View Inverse Rendering Using a Hybrid Differentiable Rendering Method
IJCAI 2023
Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement
ICCV 2023
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
ICCV 2023