PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published 19 days ago • 146
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published 7 days ago • 55
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots Paper • 2607.02646 • Published Jul 2 • 28
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning Paper • 2606.27828 • Published Jun 26 • 27
Sleeping Agents 1 Relight Five-Model Comparison 🖼 1 Compare relighting results from five image generation models
Sleeping Agents 1 Relight Five-Model Comparison 🖼 1 Compare relighting results from five image generation models
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 83
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors Paper • 2605.00658 • Published May 1 • 87