The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 4 days ago • 390
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 22 days ago • 190
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning Paper • 2610.10288 • Published 23 days ago • 19
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination Paper • 2605.22949 • Published 22 days ago • 5
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites Paper • 2610.03036 • Published 23 days ago • 18
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 26 days ago • 177
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 290
Generative Late-Interaction Embeddings For Visual Document Retrieval Paper • 2609.11808 • Published Sep 10 • 18
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Paper • 2609.03430 • Published Sep 3 • 154