Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports Paper • 2610.31158 • Published 4 days ago • 29
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 18 days ago • 245
REMORY: Learning Residual Memory for Context Compaction Paper • 2610.11287 • Published 18 days ago • 65
Closing the Context Gap: Activation Alignment for Tabular In-Context Learning Paper • 2610.06679 • Published 21 days ago • 6
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? Paper • 2609.18605 • Published Sep 16 • 41
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published Sep 14 • 52
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 371
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs Paper • 2609.11499 • Published Sep 10 • 32