🏢 Apple

Progressive Entropic Optimal Transport (PROGOT) solvers efficiently and robustly compute optimal transport plans and maps, even at large scales, by progressively scheduling parameters.

Achieving near-optimal rates for differentially private stochastic convex optimization with heavy-tailed gradients is possible using simple reduction-based techniques.

New transformation boosts privacy in online learning!

Learn optimal transport maps with structured displacements using elastic costs and a novel bilevel loss function!

Kaleido Diffusion boosts the diversity of images generated by diffusion models without sacrificing quality, using autoregressive latent modeling to add more control and interpretability to the image g…

Instance-optimal private density estimation algorithms, adapting to data characteristics for improved accuracy in the Wasserstein distance, are introduced.

Transformers struggle with complex reasoning tasks. This paper introduces ‘globality degree’ to measure task difficulty and shows that high globality hinders efficient learning. However, using ‘induc…

Researchers unveil unified architecture for grounding multimodal large language models in actions, showing superior performance with learned tokenization for continuous actions and semantic alignment …

This paper introduces dataset decomposition (DD), a novel approach to accelerate LLM training while enhancing performance. DD significantly reduces training time by decomposing datasets into buckets …

AI agents learn human-like communication, combining semantic categorization and pragmatic context-sensitive reasoning, through a novel information-theoretic framework.

Aggregate-and-Adapt Prompt Embedding (AAPE) boosts CLIP’s downstream generalization by distilling textual knowledge from natural language prompts, achieving competitive performance across various visi…