ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research Paper • 2606.07591 • Published 24 days ago • 93
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models Paper • 2605.21573 • Published May 20 • 111
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities Paper • 2510.08759 • Published Oct 9, 2025 • 46
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions Paper • 2510.08211 • Published Oct 9, 2025 • 23
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search Paper • 2509.25454 • Published Sep 29, 2025 • 147
MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning Paper • 2509.22281 • Published Sep 26, 2025 • 33
How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective Paper • 2509.18905 • Published Sep 23, 2025 • 31
InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts Paper • 2509.10813 • Published Sep 13, 2025 • 31
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling Paper • 2509.12201 • Published Sep 15, 2025 • 107
The Invisible Leash: Why RLVR May Not Escape Its Origin Paper • 2507.14843 • Published Jul 20, 2025 • 85
SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control Paper • 2505.19463 • Published May 26, 2025
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data Paper • 2507.07095 • Published Jul 9, 2025 • 56
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data Paper • 2507.07095 • Published Jul 9, 2025 • 56