Search papers, labs, and topics across Lattice.
6
1
10
0
LLMs can maintain near-perfect accuracy on long sequences with only 25% of the KV cache, thanks to a novel semantic clustering approach that dramatically improves CPU-GPU offloading.
Achieve professional-grade video mashups by mimicking a human production pipeline, using hierarchical agents to handle global structure, editing intent, and fine-grained shot selection.
By explicitly disentangling language into global context, spatial relations, and object attributes, ProVG achieves state-of-the-art remote sensing visual grounding, suggesting that fine-grained linguistic cues are key to unlocking performance in this domain.
Reconstructing videos from brain activity gets a major boost with SemVideo, which uses hierarchical semantic guidance to produce more coherent and accurate reconstructions than ever before.
Forget native sequence recovery – RIDER uses reinforcement learning to directly optimize RNA sequence design for 3D structural similarity, achieving a 100% boost in structural accuracy.
By weighting model rollouts based on predicted confidence, WIMLE achieves state-of-the-art sample efficiency in model-based RL, outperforming existing methods on complex continuous control tasks.
