Xintao Wang

ContextMaster achieves unprecedented consistency in multi-shot video creation, outperforming specialized models while processing at 16 FPS on a single GPU.

Temporal reconstruction errors can be harnessed to significantly boost video quality, eliminating the need for expensive human annotations in preference optimization.

AMFD not only outperforms traditional moment matching methods but also enables unprecedented gains in instruction-following for text-to-image generation.

Vera achieves unprecedented identity consistency in human-centric video generation, drastically reducing identity confusion in multi-person scenarios.

Unconstrained egocentric video generation now achieves unprecedented fidelity and control by disentangling hand and camera motion with a novel 3D-aware representation.

MemLearner achieves unprecedented scene consistency in video generation by learning to query context memory, outperforming traditional methods in dynamic and occluded environments.

AnchorWorld's innovative use of 3D human motion and exogenous viewpoints enables a new level of interaction fidelity in egocentric simulations, setting a new benchmark in the field.

GIM-World achieves superior long-horizon visual consistency by integrating geometry-aware implicit memory, outperforming traditional memory systems.

Generate minute-long, consistent videos with a novel memory architecture that leapfrogs existing methods by decoupling global and local memory access.

Generate multi-shot videos at 16 FPS with a single GPU and interactively steer the narrative in real-time, thanks to a novel causal architecture that overcomes the limitations of bidirectional models.