Search papers, labs, and topics across Lattice.
6
0
8
0
Achieve photorealistic, identity-consistent facial video edits from text prompts without video training data, rivaling traditional rendering software.
Fine-tune LLMs on your phone without sacrificing privacy or blowing up your data plan: pAirZero slashes memory and communication costs by using zeroth-order optimization over the air.
Ditching aggregated time series, AeroSense predicts air traffic flow with higher fidelity by directly modeling the dynamic set of individual aircraft states.
Fine-tuning VLMs for regional relevance doesn't have to sacrifice global performance: a simple data filtering and model merging technique boosts cultural relevance by 5-15% while barely impacting overall accuracy.
Radiologists' gaze patterns on real vs. AI-generated X-rays, now publicly available, reveal critical differences in how experts visually process and interpret synthetic medical imagery.
VLMs reveal that people can be looking at different places but still "seeing" the same thing, adding a crucial layer of semantic understanding to traditional eye-tracking analysis.
