activity
20242026
collaborators
Showing cs.CVShow all

16 papers · 1 filter

cs.CV2026

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models

Yi Sun, Zhiqi Zhang, Xinhao Zhong +5

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or un…

cs.CV2026

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception

Liupeng Li, Haoqian Kang, Zhenyu Lu +4

High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods stru…

cs.CV2026

CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models

Junhao Li, Xinhao Zhong, Yi sun +4

Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capability, existing VAR-based perso…

cs.CV2026

From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents

Niu Lian, Yuting Wang, Hanshu Yao +5

While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and sta…

cs.CV2026

Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning

Tianci Luo, Haohao Pan, Jinpeng Wang +5

Visual in-context learning (VICL) enables visual foundation models to handle multiple tasks by steering them with demonstrative prompts. The choice of such prompts largely influenc…

cs.CV2026

Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval

Jun Li, Xuhang Lou, Jinpeng Wang +4

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global…