A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Daman Arora, Andrea Zanette
This paper proposes using reinforcement learning to train large reasoning models to dynamically allocate inference-time compute based on task complexity, reducing inference costs while preserving accuracy.
David Johnson, Christos H. Papadimitriou, Kenneth Steiglitz
A comprehensive textbook on combinatorial optimization covering algorithms, complexity, NP-completeness, and approximation methods.
Ayeong Lee, Ethan Che, Tianyi Peng
First systematic study of the relationship between reasoning length and accuracy in LLMs, revealing a universal tradeoff and token complexity threshold.
Unknown
This paper provides a sharp theoretical analysis of model-based reinforcement learning with self-play, establishing sample complexity bounds and showing that model-based algorithms can achieve near-optimal performance in competitive environments.
Chen Shao, Elias Giacoumidis, Syed Moktacim Billah, et al.
This survey reviews machine learning applications in short-reach optical systems, introducing a taxonomy for time-series methods and addressing complexity challenges for practical deployment.
Unknown
Introduces Vitabench, a benchmark for evaluating LLM agents on versatile interactive tasks in real-world applications, capturing complexity of handling extensive information.
Alexey Natekin, Alois Knoll
This tutorial provides a comprehensive introduction to gradient boosting machines, covering methodology, model complexity, and practical applications.
J. P. HUGHES, S. Rees, S. Barret Kalindjian, et al.
This review outlines the key preclinical stages of drug discovery, from target identification to candidate selection, emphasizing the complexity and cost of developing new drugs.
Unknown
DPO fine-tunes LLMs to align with human preferences directly via a simple classification loss, eliminating RL complexity.
Unknown
Introduces Evol-Instruct, a method to generate large amounts of instruction data with varying complexity using LLMs instead of humans to fine-tune a Llama model.
Unknown
Sparse Transformers reduce attention complexity to O(n√n) via factorized attention patterns, enabling long sequence modeling.
Junsong Chen, Jincheng Yu, Yitong Li, et al.
SANA-Video 2.0 introduces hybrid linear-softmax attention and attention residuals to achieve softmax-level video quality with linear-complexity scaling, enabling 720p generation on a single GPU.