collaborators

6 papers

cs.CV2026

: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization

Lin Zhu, Yifeng Yang, Xinbing Wang +2

Recent approaches for vision-language models (VLMs) have shown remarkable success in achieving fast downstream adaptation. When applied to real-world downstream tasks, VLMs inevita…

cs.AI2026

SLASH the Sink: Sharpening Structural Attention Inside LLMs

Yiming Liu, Bin Lu, Xinbing Wang +2

Large Language Models (LLMs) show remarkable semantic understanding but often struggle with structural understanding when processing graph topologies in a serialized format. Existi…

cs.LG2026

Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle

Xu Bai, Bin Lu, Kun Zhang +4

Graph coarsening is a graph dimensionality reduction technique that aims to construct a smaller and more tractable graph while preserving the essential structural and semantic prop…

cs.CV2026

Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration

Mingtao Xian, Yifeng Yang, Qinying Gu +2

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated b…

cs.CV2026

TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection

Yifeng Yang, Jubo Feng, Jing Xu +3

Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative…

cs.LG2026

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection

Haohui Zhang, Zhiye Wang, Xiaoying Gan +2

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the a…