OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue Paper • 2609.21465 • Published Sep 18 • 49
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 223
Running on CPU Upgrade Agents 2.94k Omni Image Editor 🖼 2.94k Image edit, text to image, image upscale, remove watermark
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 106
Running on Zero Agents Featured 47 Follow the Mean (FLUX.2) 🪷 47 Training-free reference-guided generation with FLUX.2-klein