Search papers, labs, and topics across Lattice.
Soochow University
7
0
8
UMI-Bench 1.0 reveals that standardized real-world evaluations can dramatically improve the reliability of UMI-style robotic manipulation policies.
Robots can now navigate complex environments without continuous goal updates, relying solely on their internal spatial memory.
Label-Specific Distance-based Oversampling reveals that tailoring synthetic instance generation to label-specific feature relevance can drastically enhance multi-label classification performance.
By structuring diffusion-based driving models around a "scaffold" of frozen structural tokens, Fast-dDrive achieves a 12x speedup over autoregressive baselines while improving trajectory accuracy.
Medical VQA models can now reason more reliably thanks to a new framework that disentangles true causal effects from spurious correlations by jointly tackling observable and unobservable confounders.
Swap out slow, one-token-at-a-time generation in VLMs for a 6x speed boost, without sacrificing quality, using a surprisingly simple direct conversion to block-diffusion decoding.
Ditch the polarity labels: SemEval-2026's DimABSA task reveals how modeling sentiment along valence-arousal dimensions unlocks nuanced understanding in both aspect-based sentiment analysis and stance detection.
