Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning Paper • 2606.09290 • Published 27 days ago • 7
Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning Paper • 2606.09290 • Published 27 days ago • 7
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension Paper • 2602.13310 • Published Feb 10 • 9
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published May 17 • 34
Fidelity-Aware Data Composition for Robust Robot Generalization Paper • 2509.24797 • Published Sep 29, 2025 • 2
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension Paper • 2602.13310 • Published Feb 10 • 9
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models Paper • 2605.18601 • Published May 18 • 6
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models Paper • 2605.23345 • Published May 22 • 17
SCOPE Collection Model weights for SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models • 2 items • Updated May 25 • 2
CrossFPS Collection CrossFPS is the first multi-game FPS dataset with frame-aligned action telemetry. It comprises 69K clips from 7 titles with 10-DoF controller signals • 2 items • Updated May 13 • 2
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models Paper • 2605.23345 • Published May 22 • 17
SCOPE Collection Model weights for SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models • 2 items • Updated May 25 • 2