PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions Paper • 2610.40453 • Published 3 days ago • 13
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation Paper • 2610.30926 • Published 10 days ago • 61
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 39
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published Sep 8 • 32
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots Paper • 2607.02646 • Published Jul 2 • 26
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning Paper • 2606.27828 • Published Jun 26 • 26
Running Agents 1 Relight Five-Model Comparison 🖼 1 Compare relighting results from five image generation models
Running Agents 1 Relight Five-Model Comparison 🖼 1 Compare relighting results from five image generation models