activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs

Yiling Gao, Hongchen Wei, Zhenzhong Chen

In Vision-Language Models (VLMs), high-resolution images produce a large number of visual tokens, resulting in high computational costs and KV-cache overhead during inference. To a…

cs.CV2025

LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling

Zhihan Zhang, Xiang Pan, Hongchen Wei +1

Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, c…

cs.CV2025

RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries

Zhihong Tan, Jiayi Wang, Huiying Shi +3

Detecting forged remote sensing images is becoming increasingly critical, as such imagery plays a vital role in environmental monitoring, urban planning, and national security. Whi…

cs.CV2025

Training-Free Reasoning and Reflection in MLLMs

Hongchen Wei, Zhenzhong Chen

Recent advances in Reasoning LLMs (e.g., DeepSeek-R1 and OpenAI-o1) have showcased impressive reasoning capabilities via reinforcement learning. However, extending these capabiliti…

cs.CV2025

LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models

Hongchen Wei, Zhihong Tan, Yaosi Hu +2

Large Multimodal Models (LMMs) have demonstrated exceptional performance in video captioning tasks, particularly for short videos. However, as the length of the video increases, ge…

cs.CV2024

Visual Context Window Extension: A New Perspective for Long Video Understanding

Hongchen Wei, Zhenzhong Chen

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In co…