A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Gene H. Golub, Víctor Pereyra
This paper reviews 30 years of variable projection method developments for separable nonlinear least-squares problems, showing it reduces parameter space and improves conditioning for faster convergence.
Alexander Skulmowski, Kate Man Xu
This paper proposes a new perspective on extraneous cognitive load in digital learning, integrating constructive alignment to balance positive and negative effects of design factors.
Peilin Feng, Suorong Yang, Soujanya Poria
Introduces Σ-Mem, an online reliability memory for LLM-based multi-agent systems that records and updates agent competence and relationship evidence, enabling stable adaptation and improved coordination.
Huichi Zhou, Yihang Chen, Siyuan Guo, et al.
Introduces a memory-based online reinforcement learning paradigm for LLM agents that enables continual adaptation without fine-tuning the underlying LLM.
Lodewijk Gelauff, Mohak Goyal, Bhargav Dindukurthi, et al.
This paper uses an LLM alongside human annotators to rate contribution quality in online deliberations, finding the model competitive with individual humans and demonstrating its utility for evaluating nudges.
David Fournier, Hans J. Skaug, Johnoel Ancheta, et al.
ADMB is a programming framework using automatic differentiation for efficient and accurate statistical inference in highly parameterized nonlinear models.
Nicholas Baker, Hongjing Lu, Gennady Erlikhman, et al.
Deep convolutional networks classify objects using local edge features, not global shape, unlike human vision.
Zheng Zhang
A flexible camera calibration technique using a planar pattern observed at multiple orientations, with closed-form solution and nonlinear refinement.
Sebastian Bach, Alexander Binder, Grégoire Montavon, et al.
Proposes Layer-Wise Relevance Propagation (LRP) to visualize pixel contributions for nonlinear classifiers, enabling interpretable heatmaps of classification decisions.
Murray Shanahan
This paper argues that LLM-based conversational agents create an illusion of thinking but are fundamentally unlike humans.
Bernardino Romera‐Paredes, Mohammadamin Barekatain, Alexander Novikov, et al.
FunSearch pairs a pretrained LLM with an evolutionary evaluator to discover new mathematical constructions and heuristics, surpassing best-known results in extremal combinatorics and online bin packing.
Omar Shaikh, Michelle Lam, Joey Hejna, et al.
DITTO aligns LLMs to user-specific behaviors using fewer than 10 demonstrations via online imitation learning and preference optimization.