Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Paper • 2512.08478 • Published 21 days ago • 76
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning Paper • 2512.05111 • Published 26 days ago • 45
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution Paper • 2510.25726 • Published Oct 29 • 45
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs Paper • 2510.10689 • Published Oct 12 • 46
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published Oct 9 • 109
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published Oct 9 • 109