Search papers, labs, and topics across Lattice.
6
0
8
2
By explicitly enforcing action-conditioned consistency during training and distillation, MWM enables more reliable planning in imagined future spaces for embodied navigation.
Generative video models can now simulate a continuously evolving world, even when objects are out of sight, thanks to a new framework that maintains persistent global state.
RAG agents can be tricked by a "Visual Placebo Effect" where they inherit latent visual biases from foundation models, but a new memory weighting scheme can help them abstain when evidence is weak.
Key contribution not extracted.
Coding LLMs can now generate more physically plausible and dynamically rich 4D worlds, thanks to a novel closed-loop framework that iteratively refines simulation code based on physics-aware self-reflection.
Achieve zero-shot robotic manipulation by guiding a hierarchical vision-language-action model with knowledge-guided trajectory planning, outperforming existing methods and eliminating the need for real-world data collection.
