FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation Paper • 2610.36545 • Published 6 days ago • 12
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 Image-Text-to-Text • 27B • Updated 1 day ago • 703k • 513
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution Paper • 2609.37950 • Published Sep 29 • 10
Certification of Real Images through Calibrated Content Authentication Paper • 2610.05870 • Published 28 days ago • 15
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems Paper • 2610.01257 • Published Oct 1 • 19
4Director: Controlling Video World Models with Rigid 3D Geometry Paper • 2610.02160 • Published Oct 1 • 21
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses Paper • 2609.15938 • Published Sep 14 • 11
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 95
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation Paper • 2609.09076 • Published Sep 8 • 7