A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Paper • 2609.07821 • Published 11 days ago • 18
Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention Paper • 2608.21721 • Published 28 days ago • 5
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published Aug 17 • 341
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 24 days ago • 196
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published Jul 15 • 35