Search papers, labs, and topics across Lattice.
9
0
13
0
Achieving nearly 5x faster training for M-TGNNs without sacrificing accuracy could revolutionize how we handle temporal data in graph neural networks.
Achieving a response rate of 0.88 in full-duplex interactions, JoyAI-Talker redefines how empathetic voice agents can engage in natural conversations even amidst interruptions.
REFACT reduces token consumption while enhancing the density and faithfulness of reasoning traces in large language models, ensuring that every cited fact meaningfully supports the answer.
Iterative parameter estimation can slash branch deformation energy by over a third, revolutionizing how robots interact with delicate plant structures.
HoliDubber revolutionizes video dubbing by seamlessly integrating speech and sound effects from a single text prompt, outperforming traditional methods in quality and synchronization.
MemoryCard transforms long videos into coherent, topic-focused segments, boosting long-video QA accuracy by over 21% while maintaining visual-token efficiency.
Forget global context – ReAlign leverages a stronger VLM to generate *local*, reasoning-guided descriptions that boost visual document retrieval by up to 2%.
Multimodal agents can now plan more coherently and solve complex tasks thanks to a new anticipatory reasoning framework that forecasts short-horizon trajectories before acting.
Simulate tau protein spread in the brain ~10x faster with a neural operator, unlocking new possibilities for parameter inference and mechanistic discovery in Alzheimer's research.
