NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 3 days ago • 384
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 9 days ago • 539
Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching Paper • 2608.28695 • Published 15 days ago • 8
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 22 days ago • 275
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Paper • 2608.11924 • Published 30 days ago • 291
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 343
OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis Paper • 2607.25108 • Published Jul 27 • 2
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models Paper • 2607.06553 • Published Jul 9 • 20
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 173