activity
20242026
collaborators

9 papers

cs.OS2026

ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation

Shihao Wang, Jiahao Chen, Yanqi Pan +7

The prefill stage of long-context Retrieval-Augmented Generation (RAG) is severely bottlenecked by computational overhead. To mitigate this, recent methods assemble pre-calculated…

cs.CR2025

Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Space

Xingfu Zhou, Pengfei Wang

Large Language Model (LLM) agents relying on external retrieval are increasingly deployed in high-stakes environments. While existing adversarial attacks primarily focus on content…

cs.CV2025

DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers

Lizhen Wang, Zhurong Xia, Tianshu Hu +6

In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks…

cs.CV2025

GLAD: Generalizable Tuning for Vision-Language Models

Yuqi Peng, Pengfei Wang, Jianzhuang Liu +1

Pre-trained vision-language models, such as CLIP, show impressive zero-shot recognition ability and can be easily transferred to specific downstream tasks via prompt tuning, even w…

cs.CV2025

Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis

Pengfei Wang, Guohai Xu, Weinong Wang +3

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate…

cs.CV2025

Qwen2.5-VL Technical Report

Shuai Bai, Keqin Chen, Xuejing Liu +24

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative func…