Search papers, labs, and topics across Lattice.
4
0
6
6
Evaluating various models across diverse categories reveals that current models can only maintain short-term consistency that degrades significantly once objects leave the field of view, highlighting the gap between current model capabilities and robust visual memory ("seeing is not remembering"), providing guidance for future development of 4D foundation models.
Fire3D is a unified framework that takes a single RGB image or casual RGB video and transforms it into simulation-ready 3D scene assets for games and interactive applications in under a minute, and provides object-level completeness beyond existing feed-forward 3D approaches.
Proxy Policy Steering (PPS), an inference-time adaptation method that resolves the challenge of eliciting task-specific behavior from limited demonstrations without degrading their broad capabilities by training two lightweight proxy policies whose calibrated velocity-space difference steers the frozen base sampler.
Time is a learnable visual concept: models can now reason about and manipulate the flow of time in videos, opening doors to temporally controllable video generation and temporal forensics.
