Search papers, labs, and topics across Lattice.
4
0
6
4
Generative models can encode meaningful physical knowledge, achieving execution success in robot manipulation tasks even when visual quality is subpar.
Most RLVR datasets are just remixes of a few originals, and this paper shows how to trace them back to their source, revealing widespread data contamination.
Snapchat's new trend detection system proves that LLMs can successfully consolidate multimodal signals at scale to surface emerging topics from short-form video, boosting content freshness and user engagement.
Forget task-specific architectures: a single Vision-Language-Action foundation model, ABot-N0, now dominates embodied navigation across five distinct tasks.
