NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 20 days ago • 204
Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models Paper • 2609.06114 • Published 23 days ago
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance Paper • 2603.02175 • Published Mar 2 • 24
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments Paper • 2606.13681 • Published Jun 11 • 146
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 133
Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans? Paper • 2512.13281 • Published Dec 15, 2025 • 65
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Paper • 2510.25616 • Published Oct 29, 2025 • 107
Computer-Use Agents as Judges for Generative User Interface Paper • 2511.15567 • Published Nov 19, 2025 • 54
Grounding Computer Use Agents on Human Demonstrations Paper • 2511.07332 • Published Nov 10, 2025 • 107