activity
20242026
collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models

Chenyu Huang, Peng Ye, Xudong Tan +4

Efficiently enhancing the reasoning capabilities of Vision-Language Models (VLMs) by merging them with Large Reasoning Models (LRMs) has emerged as a promising direction. However,…

cs.CV2025

RegionE: Adaptive Region-Aware Generation for Efficient Image Editing

Pengtao Chen, Xianfang Zeng, Maosen Zhao +7

Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas larg…

cs.CV2025

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

Pengtao Chen, Xianfang Zeng, Maosen Zhao +5

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention…

cs.CV2025

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models

Xudong Tan, Yaoxin Yang, Peng Ye +5

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions. However, their high inference cost-…

cs.CV2025

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding

Chongjun Tu, Lin Zhang, Pengtao Chen +5

Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensi…

cs.CV2025

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models

Xudong Tan, Peng Ye, Chongjun Tu +5

Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens…