ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper β’ 2604.08523 β’ Published 2 days ago β’ 71
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper β’ 2604.07430 β’ Published 3 days ago β’ 126
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning Paper β’ 2505.22019 β’ Published May 28, 2025 β’ 12
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Paper β’ 2604.07340 β’ Published 3 days ago β’ 11