LLMs’ Library and Language Preferences in Code Generation
Explore how large language models prefer libraries and programming languages, revealing biases and optimization opportunities in AI code generation.
Large Language Models in Outpatient Referral: Challenges & Benchmarks
Explore the role of large language models in outpatient referrals, benchmarking performance, challenges, and future directions for healthcare integration.
Path Regularization Theory for Neural Networks & Double Descent
Discover a near-complete, optimal generalization theory for multilayer neural networks using path regularization and insights on the double descent phenome...
LongSpec: Efficient Lossless Speculative Decoding for Long Contexts
Discover LongSpec, a novel framework for lossless speculative decoding that boosts long-context AI model speed and efficiency with reduced memory use.
Forgery Attribution Reports for Manipulated Facial Images
Discover a new approach to detect and explain facial image manipulations with the MMTT dataset and ForgeryTalker framework.