DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
arXiv:2602.12205v2 Announce Type: replace-cross Abstract: Current unified multimodal models for image generation and editing typically rely on massive parameter scales…
Detecting Object Tracking Failure via Sequential Hypothesis Testing
arXiv:2602.12983v1 Announce Type: cross Abstract: Real-time online object tracking in videos constitutes a core task in computer vision, with wide-ranging…
Learning Native Continuation for Action Chunking Flow Policies
arXiv:2602.12978v1 Announce Type: cross Abstract: Action chunking enables Vision Language Action (VLA) models to run in real time, but naive…
Variation-aware Flexible 3D Gaussian Editing
arXiv:2602.11638v2 Announce Type: replace-cross Abstract: Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches…
Explaining AI Without Code: A User Study on Explainable AI
arXiv:2602.11159v1 Announce Type: new Abstract: The increasing use of Machine Learning (ML) in sensitive domains such as healthcare, finance, and…
Chatting with Images for Introspective Visual Thinking
arXiv:2602.11073v2 Announce Type: replace-cross Abstract: Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual…