Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception Paper • 2610.37037 • Published 24 days ago • 29
World Model Interpretability: From Decoding Representations to Understanding Latent Worlds Paper • 2610.25296 • Published Oct 18 • 7
DLite Collection History-free Speculative Decoding for Agentic AI • 5 items • Updated 23 days ago • 6
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows Paper • 2604.15715 • Published Apr 17 • 4
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents Paper • 2601.18130 • Published Jan 26 • 2
NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window? Paper • 2407.11963 • Published Jul 16, 2024 • 41