Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published 6 days ago • 55
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Paper • 2604.27393 • Published Apr 30 • 77
view article Article EMO: Pretraining mixture of experts for emergent modularity allenai • 27 days ago • 38
VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs Paper • 2603.23481 • Published Mar 24 • 7
Nested Learning: The Illusion of Deep Learning Architectures Paper • 2512.24695 • Published Dec 31, 2025 • 46
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing Paper • 2512.14681 • Published Dec 16, 2025 • 44
Efficient Long-context Language Model Training by Core Attention Disaggregation Paper • 2510.18121 • Published Oct 20, 2025 • 124
lmgame-Bench: How Good are LLMs at Playing Games? Paper • 2505.15146 • Published May 21, 2025 • 20
Faster Video Diffusion with Trainable Sparse Attention Paper • 2505.13389 • Published May 19, 2025 • 38
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Paper • 2401.09670 • Published Jan 18, 2024 • 2
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks Paper • 2502.08235 • Published Feb 12, 2025 • 59
Fast Video Generation with Sliding Tile Attention Paper • 2502.04507 • Published Feb 6, 2025 • 51
Efficiently Serving LLM Reasoning Programs with Certaindex Paper • 2412.20993 • Published Dec 30, 2024 • 36