StopLoss: Teaching Agents to Predict Failure and Stop Early Paper • 2610.25525 • Published Oct 18 • 16
Running on Zero Agents Featured 17 PixelUMM 🎨 17 Encoder-free unified image/video understanding + generation
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published Sep 29 • 29
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published Sep 29 • 29
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published Sep 29 • 29
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 52
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 52
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published Jul 14 • 41
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 39
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published Jul 14 • 41
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 39 • 4
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 39