StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling Paper • 2507.05240 • Published Jul 7 • 46
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training Paper • 2506.05301 • Published Jun 5 • 55
WORLDMEM: Long-term Consistent World Simulation with Memory Paper • 2504.12369 • Published Apr 16 • 33
Trajectory Attention for Fine-grained Video Motion Control Paper • 2411.19324 • Published Nov 28, 2024 • 12