Search papers, labs, and topics across Lattice.
5
0
9
6
Video-LLMs can achieve up to 2.65x faster time-to-first-token and 61% FLOPs reduction by compressing visual tokens *inside* the vision encoder, not just after.
By unifying specialized detectors with MLLMs in an agentic framework, Echo-{\alpha} achieves state-of-the-art ultrasound interpretation, suggesting a path to more accurate, interpretable, and transferable medical AI.
LLM agents can be made more reliable by structurally verifying their internal reasoning, rather than relying on consensus which conflates agreement with faithfulness.
Forget one-to-one video segment alignments: this new framework leverages global video context to significantly improve multimodal translation, especially for long videos.
Forget slow, suboptimal SVD compression: Swift-SVD delivers theoretically optimal low-rank LLM compression with 3-70x speedups.
