9 papers
Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment
Haotian Deng, Wenbin Xing, Gang Xu +5
Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existi…
MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models
Yuansheng Gao, Wenbin Xing, Jiahao Yuan +4
Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully suppor…
CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction
Mengran Li, Bo Li, Jiaying Wang +13
Cellular perturbation-response modeling requires coordinated choices of representations, fusion mechanisms, objectives, and training procedures. Large language models (LLMs) can pr…
Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
Wenbin Xing, Quanxing Zha, Lizheng Zu +3
Current research on video hallucination mitigation primarily focuses on isolated error types, leaving compositional hallucinations, arising from incorrect reasoning over multiple i…
Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models
Yuansheng Gao, Jinman Zhao, Tong Zhang +5
Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing inference-time intervention methods u…
Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling
Mengran Li, Zelin Zang, Wenbin Xing +4
Understanding how chemical perturbations propagate through biological systems is essential for robust molecular property prediction. While most existing methods focus on chemical s…
A Survey of Large Language Models for Data Challenges in Graphs
Mengran Li, Pengyu Zhang, Wenbin Xing +11
Graphs are a widely used paradigm for representing non-Euclidean data, with applications ranging from social network analysis to biomolecular prediction. While graph learning has a…
MM-STFlowNet: A Transportation Hub-Oriented Multi-Mode Passenger Flow Prediction Method via Spatial-Temporal Dynamic Graph Modeling
Ronghui Zhang, Wenbin Xing, Mengran Li +5
Accurate and refined passenger flow prediction is essential for optimizing the collaborative management of multiple collection and distribution modes in large-scale transportation…
AttriReBoost: A Gradient-Free Propagation Optimization Method for Cold Start Mitigation in Attribute Missing Graphs
Mengran Li, Chaojun Ding, Junzhou Chen +7
Missing attribute issues are prevalent in the graph learning, leading to biased outcomes in Graph Neural Networks (GNNs). Existing methods that rely on feature propagation are pron…