A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Antoine Daina, Vincent Zoete
The BOILED-Egg model predicts gastrointestinal absorption and brain penetration of small molecules using only lipophilicity and polarity descriptors, with a clear graphical output.
Unknown
EvaluLLM is a tool for LLM-assisted evaluation of generative outputs that helps users understand evaluation risks and set appropriate expectations.
Unknown
The paper compares input-level test-time augmentation against output-level sampling for LLMs at matched compute, finding input diversity yields better accuracy.
Canbin Huang, Tianyuan Shi, Yuhua Zhu, et al.
Lookahead routing predicts latent representations of potential model outputs to guide LLM selection, improving routing decisions without full inference.
Yang Sui, Yu-Neng Chuang, Guanchu Wang, et al.
This survey systematically categorizes and reviews methods for efficient reasoning in LLMs, addressing the overthinking phenomenon by optimizing models, outputs, and input prompts.
Geoffrey J. Barton
ALSCRIPT is a tool for formatting multiple sequence alignments, providing a flexible command language to control layout and annotation for publication-quality output.
Ioannis Tsochantaridis, Thorsten Joachims, Thomas Hofmann, et al.
This paper generalizes maximum-margin classification to structured and interdependent output spaces, proposing a cutting plane algorithm that solves the resulting exponential-constraint quadratic program in polynomial time.
Erik Johannes Husom, Arda Göknil, Merve Astekin, et al.
This paper evaluates 28 quantized LLMs on a Raspberry Pi 4, measuring energy efficiency, accuracy, and latency to identify optimal configurations for sustainable edge AI deployment.
Zixuan Ke, Fangkai Jiao, Yifei Ming, et al.
A survey categorizing LLM reasoning methods along regimes (inference-time vs training) and architectures (standalone vs agentic), analyzing input/output-level techniques and trends.
Haotian Wang, Han Zhao, Shuaiting Chen, et al.
This paper proposes using outputs from reasoning-intensive LLMs to improve non-reasoning models via supervised fine-tuning, showing consistent benchmark gains.
Unknown
This paper describes standard recipes for building and training vision-language-action models (VLAs) that adapt VLMs to output robot actions, enabling fast training, fast inference, and better generalization.
Unknown
Direct3D introduces a scalable 3D latent diffusion transformer for image-to-3D generation, achieving strong generalization and high-quality 3D outputs.