Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published 6 days ago • 57
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Paper • 2608.05102 • Published 6 days ago • 64
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation Paper • 2607.24731 • Published 15 days ago • 76
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation Paper • 2607.24731 • Published 15 days ago • 76
Running on Zero Agents Featured 153 LTX 2.3 First-Last Frame 🎥 153 Generate videos from text, images, and audio
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 88
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields Paper • 2606.11042 • Published Jun 9 • 22
Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding Paper • 2512.06673 • Published May 9
SearchGen Collection Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation • 4 items • Updated 26 days ago • 5
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 88 • 4