The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 27 days ago • 52
U-Space: Uncovering When and Why Uncertainty Arises in Language Models Paper • 2610.09087 • Published Oct 6 • 45
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 49
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications Paper • 2609.10539 • Published Sep 9 • 4
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs Paper • 2609.11499 • Published Sep 10 • 9
Agentic Visual Generation: From Generative Models to Agentic Control Paper • 2609.06758 • Published Sep 6 • 21
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published Sep 4 • 13
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation Paper • 2608.18565 • Published Aug 19 • 20
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published Aug 14 • 117
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation Paper • 2608.13489 • Published Aug 13 • 86
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 25
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal Paper • 2608.05565 • Published Aug 6 • 14
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents Paper • 2608.05013 • Published Aug 4 • 35
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation Paper • 2608.02287 • Published Aug 3 • 27