Search papers, labs, and topics across Lattice.
5
0
7
5
Surpassing existing benchmarks, SpatialAvatar-0 achieves superior 4D head avatar quality with up to 60x fewer training iterations than traditional methods.
Representation misalignment is the hidden bottleneck in multimodal sentiment analysis, and aligning modalities before fusion can yield superior performance.
A single framework can eliminate all major write-time anomalies in LLM agents while preserving the integrity of belief updates.
Vision-based robot learning struggles with occlusions, but UMI-3D's clever wrist-mounted LiDAR unlocks robust manipulation in cluttered real-world environments.
Achieve near-dense Video-LLM performance on long videos with up to 57% fewer FLOPs by adaptively selecting which video cubes and tokens to process.
