WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper • 2603.16871 • Published 1 day ago • 50
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation Paper • 2510.23581 • Published Oct 27, 2025 • 42
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 2 days ago • 122
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 2 days ago • 122 • 4
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 2 days ago • 122
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 2 days ago • 122
Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory Paper • 2601.16296 • Published Jan 22 • 28
Exploring Conditions for Diffusion models in Robotic Control Paper • 2510.15510 • Published Oct 17, 2025 • 40
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation Paper • 2510.23581 • Published Oct 27, 2025 • 42
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation Paper • 2510.23581 • Published Oct 27, 2025 • 42 • 2
Fine-Grained Perturbation Guidance via Attention Head Selection Paper • 2506.10978 • Published Jun 12, 2025 • 25
Runtime error Featured 2.01k Chat With Janus-Pro-7B 🌍 2.01k A unified multimodal understanding and generation model.