SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video Paper • 2609.37969 • Published 1 day ago • 18
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? Paper • 2609.38079 • Published 1 day ago • 30
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing Paper • 2609.23784 • Published 11 days ago • 14
Paint-Anything: Unified Any-Color Control for Image Generation and Editing Paper • 2609.20816 • Published 14 days ago • 57
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 14 days ago • 138
OpenVE inference results Collection VideoCoF OPD 的 OpenVE-Bench 推理结果,供 openve-watcher 爬取并用 Gemini 打分 • 70 items • Updated about 1 hour ago • 1
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models Paper • 2609.02886 • Published 29 days ago • 118
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models Paper • 2608.16887 • Published Aug 17 • 36
From SRA to Self-Flow: Data Augmentation or Self-Supervision? Paper • 2607.02508 • Published Jul 2 • 13
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing Paper • 2606.26740 • Published Jun 25 • 82