Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
5
SAM-V introduces a prompt-fusion mechanism that enriches sparse SAM prompt tokens with view-specific camera tokens and local VGGT features, making the prompt representation both view-aware and spatially grounded, together with a mask decoder that attends to dense 2D and 3D features.
ReToken boosts vision-language model performance by over 20% on key benchmarks while fitting training and inference within a single GPU's memory constraints.
Fine-tuning LLMs can make them *more* likely to hallucinate facts they already knew, but self-distillation offers a surprisingly simple fix.
