Search papers, labs, and topics across Lattice.
8
0
12
Identifying architectural flaws through PairSmell can lead to substantial improvements in software modularization, with machine learning models achieving a 58.6% boost in predictive accuracy.
Supervised fine-tuning with domain-specific data can drastically enhance the reliability of LLM-generated Solidity smart contracts, outperforming general-purpose models.
Forget patch-based image tokenization: channel-wise quantization unlocks better codebook utilization and text-to-image generation by representing images as discrete levels of visual detail.
Freezing your vision foundation model doesn't have to mean sacrificing fine-grained detail: DecQ unlocks improved reconstruction and faster generative convergence with just 8 extra queries and minimal overhead.
VideoLLMs leak training data: a novel black-box attack recovers membership with surprisingly high accuracy (AUC=0.68) by probing generation brittleness across temperatures.
Self-improving navigation agents can get lost in their own exploration unless you carefully balance behavioral diversity with learning stability, as shown by a new method that outperforms prior VLN models.
Instruction understanding can evolve dynamically with context, leading to a notable +2.68% SPL improvement in navigation tasks.
AI spots a hidden pattern in lung scans of lupus patients, revealing that specific airway dilations in the upper lobes could be a telltale sign of interstitial lung disease.
