A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Rahul Raguram, Ondřej Chum, Marc Pollefeys, et al.
USAC extends RANSAC with a universal framework integrating advanced sampling, verification, and model refinement for robust estimation.
Zhisheng Hu, Minghui Zhu, Peng Liu
Proposes an adaptive cyber defense using learning-based POMDP with Thompson sampling to counter multi-stage attacks under unknown exploit likelihoods and impacts.
Luming Zhang, Mingli Song, Qi Zhao, et al.
This paper introduces graphlets (small connected subgraphs) to represent aesthetic features and proposes a probabilistic model for automatic photo cropping via Gibbs sampling.
John Skilling
Nested sampling directly estimates the evidence by integrating likelihood over prior mass, with posterior samples as a by-product, and handles phase-change problems that defeat thermal annealing.
Maarten Blaauw, J. Andrés Christen
Introduces Bacon, a Bayesian autoregressive gamma process for flexible paleoclimate age-depth modeling with robust MCMC sampling.
Aayush Karan, Yilun Du
Proposes a simple iterative sampling algorithm that elicits reasoning from base LLMs at inference time, matching or outperforming RL post-training on single-shot tasks without additional training or verifiers.
Unknown
QALIGN uses MCMC sampling and Minimum Bayes Risk to align language model outputs at test time without retraining.
Unknown
Eagle 2.5 introduces a generalist vision-language model family with Automatic Degrade Sampling and Image Area Preservation for long-context video and high-resolution image understanding.
Unknown
CodeGen2 unifies model architectures, learning methods, infill sampling, and data distributions to improve LLM training efficiency for program synthesis.
Unknown
Introduces speculative decoding, an algorithm for faster sampling from autoregressive models by computing multiple tokens in parallel without altering outputs.
Stuart Hadfield, Zhihui Wang, Bryan O’Gorman, et al.
Extends the quantum approximate optimization algorithm to a quantum alternating operator ansatz with more general families of unitaries for broader optimization and sampling problems.
Justin Johnson, Taghi M. Khoshgoftaar
This survey examines deep learning techniques for class imbalance, finding limited research focused on computer vision with CNNs and noting traditional methods like data sampling remain applicable.