🏢 UC Davis

New streaming algorithms for instrumental variable regression achieve fast convergence rates, solving the problem efficiently without matrix inversions or mini-batches, enabling real-time causal analy…

SAND, a novel transformer network variant, smoothly imputes sparse and noisy functional data by leveraging self-attention on derivatives, outperforming existing methods.

PREPARED efficiently edits DNNs to provably satisfy properties by relaxing the problem to a linear program, minimizing parameter changes.

Researchers developed novel methods to improve the generation of adversarial examples against safety-aligned LLMs, achieving significantly higher attack success rates compared to existing techniques.

Deep random features enable efficient Euclidean distance compression, offering improved bit storage compared to linear methods for specific parameter ranges, thus significantly advancing high-dimensio…