English
Related papers

Related papers: Iterate to Accelerate: A Unified Framework for Ite…

200 papers

Self-improvement is a critical capability for large language models and other intelligent systems, enabling them to refine their behavior and internal consistency without external supervision. Despite its importance, prior approaches…

Machine Learning · Computer Science 2025-11-12 Mehryar Mohri , Jon Schneider , Yifan Wu

Measuring how quickly iterative methods converge is essential in computational mathematics, but current approaches have significant limitations. Q-order analysis requires strict smoothness conditions, while R-order analysis lacks precision…

Numerical Analysis · Mathematics 2025-04-09 Xiangmin Jiao , Hongji Gao

Large pre-trained models exhibit distinct and complementary capabilities dependent on the data they are trained on. Language models such as GPT-3 are capable of textual reasoning but cannot understand visual information, while vision models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Shuang Li , Yilun Du , Joshua B. Tenenbaum , Antonio Torralba , Igor Mordatch

Recent Iterated Response (IR) models of pragmatics conceptualize language use as a recursive process in which agents reason about each other to increase communicative efficiency. These models are generally defined over complete utterances.…

Computation and Language · Computer Science 2018-10-23 Reuben Cohn-Gordon , Noah D. Goodman , Christopher Potts

Recently, there has been significant progress in the development of distributed first order methods. (At least) two different types of methods, designed from very different perspectives, have been proposed that achieve both exact and linear…

Information Theory · Computer Science 2017-12-27 Dusan Jakovetic

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Machine Learning · Computer Science 2026-03-06 Ruiqi Zhang , Daman Arora , Song Mei , Andrea Zanette

In many iterative optimization methods, fixed-point theory enables the analysis of the convergence rate via the contraction factor associated with the linear approximation of the fixed-point operator. While this factor characterizes the…

Systems and Control · Electrical Eng. & Systems 2022-06-22 Trung Vu , Raviv Raich

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce…

Artificial Intelligence · Computer Science 2026-04-10 Zhicheng Yang , Zhijiang Guo , Yinya Huang , Yongxin Wang , Wenlei Shi , Yiwei Wang , Xiaodan Liang , Jing Tang

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Fulin Shi , Wenyi Xiao , Bin Chen , Liang Din , Leilei Gan

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Machine Learning · Computer Science 2024-11-01 Arihan Yadav , Alan McMillan

While multi-modal learning has advanced significantly, current approaches often create inconsistencies in representation and reasoning of different modalities. We propose UMaT, a theoretically-grounded framework that unifies visual and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Xiaowei Bi , Zheyuan Xu

We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent…

Machine Learning · Computer Science 2012-02-20 Michael Gutmann , Jun-ichiro Hirayama

It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point…

Optimization and Control · Mathematics 2026-04-22 Yu-Wen Chen , Can Kizilkale , Murat Arcak

Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like…

Computation and Language · Computer Science 2025-04-22 Lingrui Mei , Shenghua Liu , Yiwei Wang , Baolong Bi , Yuyao Ge , Jun Wan , Yurong Wu , Xueqi Cheng

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

Software Engineering · Computer Science 2026-03-24 Balaji Dinesh Gangireddi , Aniketh Garikaparthi , Manasi Patwardhan , Arman Cohan

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view…

Artificial Intelligence · Computer Science 2026-04-01 Chao Wu , Baoheng Li , Mingchen Gao , Yu Tian , Zhenyi Wang

Iterative algorithms based on thresholding, feedback and null space tuning (NST+HT+FB) for sparse signal recovery are exceedingly effective and fast, particularly for large scale problems. The core algorithm is shown to converge in finitely…

Numerical Analysis · Mathematics 2017-11-08 Ningning Han , Shidong Li , Zhanjie Song , Hong Wang

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or…

Artificial Intelligence · Computer Science 2024-12-30 Sijia Chen , Baochun Li

Classical mathematical models of information sharing and updating in multi-agent networks use linear operators. In the paradigmatic DeGroot model, agents update their states with linear combinations of their neighbors' current states. In…

Systems and Control · Electrical Eng. & Systems 2022-04-26 Aditya Bhaskar , Shriya Rangarajan , Vikram Shree , Mark Campbell , Francesca Parise

We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a…

Machine Learning · Statistics 2017-05-23 Renbo Zhao , William B. Haskell , Jiashi Feng