A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Andrew Birrell, Bruce Jay Nelson
This paper describes the design and implementation of a remote procedure call (RPC) package, covering binding, transport protocol, optimizations, and performance measurements.
Robert Hooke, T. A. Jeeves
Introduces the direct search method, a derivative-free optimization algorithm for numerical and statistical problems, foundational to modern pattern search methods.
Hideyuki Takagi
A comprehensive survey of interactive evolutionary computation (IEC), covering applications and interface research to reduce human fatigue, based on about 250 papers.
Emilien Dupont, Marvin Eisenberger, Borislav Kozlovskii, et al.
This paper improves the matrix multiplication exponent upper bound to ω < 2.371177 using a reformulated optimization problem and a new ML-based optimization algorithm refined with AlphaEvolve.
Yaxin Luo, Haobin Jiang, Jialv Zou, et al.
AutoDesign introduces a meta-harness optimization framework for long-horizon agentic design, achieving state-of-the-art paper-to-poster generation with recursive self-improvement.
Mehdi Fatemi, Banafsheh Rafiee, Mingjie Tang, et al.
This paper shows that verbosity in reasoning models is an optimization artifact of RL loss minimization on incorrect answers, and proposes a two-phase RL procedure to reduce response length while preserving accuracy.
Chujie Zheng, Shixuan Liu, Mingze Li, et al.
GSPO defines sequence-level importance ratios and clipping for stable, efficient RL training of LLMs, outperforming GRPO and stabilizing MoE training.
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
Introduces parameter-space exploration for LLM RL via Perturbed Parameter Policy Optimization (3PO), improving downstream performance over GRPO at similar FLOPs.
Ling Yue, K. Bhandari, Ching-Yun Ko, et al.
This survey reviews methods for designing and optimizing LLM agent workflows, treating them as agentic computation graphs and organizing literature by when workflow structure is determined.
Michael L. Fredman, Robert E. Tarjan
Introduces Fibonacci heaps, a priority queue data structure with O(1) amortized time for most operations, improving network optimization algorithms.
David Johnson, Christos H. Papadimitriou, Kenneth Steiglitz
A comprehensive textbook on combinatorial optimization covering algorithms, complexity, NP-completeness, and approximation methods.
Taiwo Samuel Ajani, Agbotiname Lucky Imoize, Aderemi A. Atayero
A survey of optimization techniques for implementing machine learning algorithms on resource-constrained embedded and mobile devices, covering algorithms, hardware, and applications.