Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published 1 day ago • 3
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising Paper • 2604.26694 • Published 1 day ago • 2
ClawGym: A Scalable Framework for Building Effective Claw Agents Paper • 2604.26904 • Published 1 day ago • 33
IAM: Identity-Aware Human Motion and Shape Joint Generation Paper • 2604.25164 • Published 2 days ago • 1
Toward Scalable Terminal Task Synthesis via Skill Graphs Paper • 2604.25727 • Published 2 days ago • 6
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios Paper • 2604.25914 • Published 2 days ago • 37
SketchVLM: Vision language models can annotate images to explain thoughts and guide users Paper • 2604.22875 • Published 7 days ago • 28
Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data Paper • 2604.24479 • Published 3 days ago • 4
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published 3 days ago • 61
Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Paper • 2604.22782 • Published 27 days ago • 4
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation Paper • 2604.23099 • Published 5 days ago • 2
SketchVLM: Vision language models can annotate images to explain thoughts and guide users Paper • 2604.22875 • Published 7 days ago • 28
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model Paper • 2604.22152 • Published 6 days ago • 3
AgentSearchBench: A Benchmark for AI Agent Search in the Wild Paper • 2604.22436 • Published 6 days ago • 10
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published 6 days ago • 212
WorldMark: A Unified Benchmark Suite for Interactive Video World Models Paper • 2604.21686 • Published 7 days ago • 36