12 papers
Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control
Zibo Wang, Haochen Han, Pengzhen Ren +2
Diffusion and flow-matching Vision-Language-Action (VLA) policies generate action chunks through iterative denoising, incurring substantial inference latency that severely limits r…
DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction
Hongbo Duan, Pengting Luo, Chengzhi Zhao +3
We present DynActiveGS, a dynamic-aware active reconstruction framework based on 3D Gaussian Splatting (3DGS) for autonomous exploration in dynamic environments. The framework incr…
VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Yining Sun, Haoyu Kang, Jiajun Wu +7
Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as…
Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
Haochen Han, Jue Wang, Alex Jinpeng Wang +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to comprehend negation remains underexplo…
Pulse: Training Acceleration for Large Diffusion Models with Automatic Pipeline Parallelism
Boran Sun, Guoyong Jiang, Lin Zhang +8
Diffusion models are now a dominant approach for high-fidelity image and video generation, yet scaling their training across GPU clusters remains challenging. Unlike transformer-on…
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Lingxuan Wu, Zijian Zhu, Lizhong Wang +5
Diffusion policies have achieved remarkable success in robotic manipulation, yet they often fail to satisfy strict physical constraints required for safe deployment. Existing appro…
NavCrafter: Exploring 3D Scenes from a Single Image
Hongbo Duan, Peiyu Zhuang, Yi Liu +5
Creating flexible 3D scenes from a single image is vital when direct 3D data acquisition is costly or impractical. We introduce NavCrafter, a novel framework that explores 3D scene…
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
Jiacheng Hou, Yining Sun, Ruochong Jin +4
Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual i…
TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering
Rui Gui, Yang Wan, Haochen Han +4
Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. H…
Negation-Aware Test-Time Adaptation for Vision-Language Models
Haochen Han, Alex Jinpeng Wang, Fangming Liu +1
In this paper, we study a practical but less-touched problem in Vision-Language Models (VLMs), \ie, negation understanding. Specifically, many real-world applications require model…
Unlearning the Noisy Correspondence Makes CLIP More Robust
Haochen Han, Alex Jinpeng Wang, Peijun Ye +1
The data appetite for Vision-Language Models (VLMs) has continuously scaled up from the early millions to billions today, which faces an untenable trade-off with data quality and i…
Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
Zhuobai Dong, Junchao Yi, Ziyuan Zheng +5
Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While…