2026 顶会论文
9作者位次 #2/2ICML 2026Poster· Deep Learning / Large Language Models
SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling
Xiang Fang · Wanlong Fang
一作ICML 2026Poster· Deep Learning / Large Language Models
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
Wanlong Fang · Tianle Zhang · Wen Tao · Alvin Chan
作者位次 #2/3ICML 2026Poster· Deep Learning / Large Language Models
Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness
Xiang Fang · Wanlong Fang · Wei Ji
作者位次 #2/3CVPR 2026Poster· Computer Vision & Pattern Recognition
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning
Xiang Fang · Wanlong Fang · Changshuo Wang
作者位次 #2/7AAAI 2026Poster· Artificial Intelligence
Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs
Xiang Fang · Wanlong Fang · Changshuo Wang · Keke Tang · Daizong Liu · Siyi Wang · Wei Ji
作者位次 #2/3AAAI 2026Poster· Artificial Intelligence
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
Xiang Fang · Wanlong Fang · Changshuo Wang
作者位次 #2/2AAAI 2026Poster· Artificial Intelligence
Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security
Xiang Fang · Wanlong Fang
作者位次 #2/5AAAI 2026Poster· Artificial Intelligence
Rethinking Video-Language Model from the Language Input Perspective
Xiang Fang · Wanlong Fang · Changshuo Wang · Xiaoye Qu · Daizong Liu
一作AAAI 2026Poster· Artificial Intelligence
To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance
Wanlong Fang · Tianle Zhang · Alvin Chan