activity
20242026
collaborators

16 papers

cs.CV2026

Messages, Not Tokens: Grounded Coresets for Faithful VLM Compression

Long Qian, Jiaqi Wei, Bingke Zhu +2

Modern vision language models (VLMs) turn high-resolution images into long sequences of visual tokens. Every token traverses the language decoder and persists in its prompt KV cach…

cs.CV2026

UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction

Zhaopeng Gu, Bingke Zhu, Zhaowen Li +5

Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the k…

cs.CL2026

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing

Yongqi An, Chang Lu, Kuan Zhu +5

Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences.…

cs.SD2026

Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning

Linge Wang, Yingying Chen, Bingke Zhu +2

Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, jointly optimizing these object…

cs.CV2026

FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization

Zhaopeng Gu, Bingke Zhu, Guibo Zhu +3

Anomaly detection methods typically require extensive normal samples from the target class for training, limiting their applicability in scenarios that require rapid adaptation, su…

cs.CV2026

FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization

Zhaopeng Gu, Bingke Zhu, Guibo Zhu +4

Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing ap…