Search papers, labs, and topics across Lattice.
Optimizing for runtime in multimodal training can be energy-inefficient, as data movement and overlap on Grace Hopper chips dominate energy consumption, not raw compute.
Forget grid layouts: Map2World lets you generate consistent 3D worlds from arbitrary segment maps, offering unprecedented control and scalability.
A groundbreaking framework reduces false positives in recommendation systems by over 74%, restoring user control and transparency in content curation.
Iterative visual refinement lets agents navigate dense coding IDEs with superhuman precision, outperforming single-shot methods and paving the way for more reliable software engineering agents.
Gaze-tracking unlocks a new level of personalized AI assistance, enabling LLMs to infer user cognitive states and boost recall performance.
GeoAI assistants remain unproductive because they lack a crucial agency layer for iterative human-AI collaboration, a gap this paper addresses with nine core primitives.
Synthetic motion data, when represented as optical flow, unlocks a new level of realism and control in video diffusion models, surpassing the limitations of real-world datasets.
Ditch mean pooling in your geospatial foundation models: richer pooling methods like GeM can boost accuracy by up to 5% and slash the geographic generalization gap by 40%.
Forget slow, reactive GUI agents – ActionEngine uses a state-machine memory to plan actions programmatically, slashing costs by 11.8x and doubling speed while boosting task success to 95%.
Forget task-specific models: Magma, a single foundation model, now outperforms them in both UI navigation and robotic manipulation by bridging verbal and action abilities.
