OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 2 days ago • 15
TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion Paper • 2609.38653 • Published 3 days ago • 25
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively? Paper • 2609.39578 • Published 2 days ago • 38
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published 4 days ago • 111