Wanggui He
14 papers · 2025–2026 · 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (27) β Rising Star (14)
π
Keyword Champion
(2)
π€
Dynamic Duo
(13)
β‘
Prolific Year Β· Prolific
ποΈ
Keyword Collector
(76)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Machine Learning
(8)
Computer Vision
(6)
Deep Learning
(6)
Generation
(5)
Learning Types Β· Machine Learning
(4)
Models
(4)
Application Areas
(3)
Natural Language Processing
(2)
Applications
(2)
Architectures
(2)
Core Methods
(2)
Learning Types Β· Deep Learning
(2)
Reinforcement Learning
(1)
Keywords
diffusion model
(4)
image generation
(4)
vision-language model
(3)
direct preference optimization
(2)
image editing
(2)
visual question answering
(2)
large language model
(2)
image personalization
(2)
multimodal large language model
(2)
mathematical reasoning
(1)
semantic analysis
(1)
multimodal learning
(1)
image reconstruction
(1)
multi-task learning
(1)
factuality evaluation
(1)
knowledge distillation
(1)
feature extraction
(1)
generative model
(1)
semantic alignment
(1)
text-to-image generation
(1)
Papers
CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
AAAI 2026
FUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and Generation
AAAI 2026
Unified Personalized Understanding, Generating and Editing
CVPR 2026
Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
ICCV 2025
Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
AAAI 2025
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
ICML 2025
LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
ICLR 2025
MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis
AAAI 2025
MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
ICLR 2025
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
CVPR 2025
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
ICLR 2025
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
ACL 2025
TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition
ACL 2025
TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance
CVPR 2025