Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published 4 days ago • 207
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 2 days ago • 27
ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing Paper • 2609.38541 • Published 3 days ago • 25
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies Paper • 2609.38537 • Published 3 days ago • 28