A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Lailong Luo, Deke Guo, Richard T. B. Ma, et al.
A comprehensive survey of over 60 Bloom filter variants, analyzing optimization techniques for performance and generalization, and outlining future design trends.
Unknown
This paper shows that Process Reward Models can generalize from mathematical reasoning to code, enhancing LLM reasoning in test-time scaling across domains.
Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca, et al.
Tiny Aya L2-Thinker achieves over 93% in-language reasoning across 60 languages via data mixing in SFT, without reasoning supervision in every target language.
Xiaofeng Wu, Alan Ritter, Wei Xu
This paper introduces a taxonomy of tabular input representations and table understanding tasks, highlighting critical gaps including retrieval-focused tasks, challenges with complex structures, and limited generalization.
Nour Shaheen, Junwei Ma, Alex Labach, et al.
This paper investigates why tabular foundation models generalize surprisingly well in in-context learning, proposing a theoretical framework and empirical analysis to explain their performance.
Richard S. Sutton
This paper presents positive results for all control tasks previously reported as failures by Boyan and Moore, using sparse-coarse-coded function approximators (CMACs) and online learning.
A. G. Wilson
This paper argues that deep learning's anomalous generalization behaviors are not unique or mysterious, and can be explained by soft inductive biases within classical frameworks like PAC-Bayes.
Unknown
This paper demonstrates that tabular foundation models can achieve generalization through in-context learning from a single table, without requiring pre-training on multiple tables.
Unknown
Proposes invariant Causal Representation Learning (iCaRL) for out-of-distribution generalization in nonlinear settings.
Unknown
RoboNet is a large-scale multi-robot learning dataset and benchmark that enables sharing of robotic data across institutions to improve generalization in robot learning.
Unknown
DreamGen introduces a pipeline that uses state-of-the-art video generative models to create synthetic videos and extract pseudo-actions, enabling generalization in robot learning.
Unknown
Villa-x enhances latent action modeling in Vision-Language-Action models to improve robot manipulation policy learning and generalization.