English
Related papers

Related papers: Inverse-Free Wilson Loops for Transformers: A Prac…

200 papers

Large language models (LLMs) are fluent but largely static after pre-training; new or shifting knowledge is typically added with retrieval-augmented generation (RAG) or fine-tuning. RAG raises latency and engineering overhead and often…

Artificial Intelligence · Computer Science 2025-12-23 Rimom Costa

Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early turns can propagate across subsequent turns, undermining…

Computation and Language · Computer Science 2025-08-28 Yiming Du , Yifan Xiang , Bin Liang , Dahua Lin , Kam-Fai Wong , Fei Tan

Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods leveraging pretrained denoisers, and unrolled architectures…

Image and Video Processing · Electrical Eng. & Systems 2026-03-31 Matthieu Terris , Samuel Hurault , Maxime Song , Julian Tachella

Gauge fixing is an essential step in lattice QCD calculations, particularly for studying gauge-dependent observables. Traditional iterative algorithms are computationally expensive and often suffer from critical slowing down and scaling…

High Energy Physics - Lattice · Physics 2026-03-05 Ho Hsiao , Benjamin J. Choi , Hiroshi Ohno , Akio Tomiya

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate…

Robotics · Computer Science 2025-10-31 Guanxing Lu , Rui Zhao , Haitao Lin , He Zhang , Yansong Tang

Statisticians generally use ordinary least squares to minimize the random error in a subject response with respect to independent explanatory variable. However, Wooten shows illustrates how ordinary least squares can be used to minimize the…

Methodology · Statistics 2016-03-28 Rebecca D. Wooten

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

Machine Learning · Computer Science 2025-05-20 Fei Lu , Yue Yu

A full performance analysis of the widely linear (WL) minimum variance distortionless response (MVDR) beamformer is introduced. While the WL MVDR is known to outperform its strictly linear counterpart, the Capon beamformer, for noncircular…

Information Theory · Computer Science 2021-12-01 Zhe Li , Rui Pu , Yili Xia , Wenjiang Pei , Danilo P. Mandic

O'Hearn's Incorrectness Logic (IL) has sparked renewed interest in static analyses that aim to detect program errors rather than prove their absence, thereby avoiding false alarms -- a critical factor for practical adoption in industrial…

Logic in Computer Science · Computer Science 2026-01-23 Flavio Ascari , Roberto Bruni , Roberta Gori , Azalea Raad

Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e., training and test data share the same style of the input…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yang Li , Aming Wu , Zihao Zhang , Yahong Han

We argue that the sharp-cutoff Wilson renormalization group provides a powerful tool for the analysis of second-order and weakly first-order phase transitions. In particular, in a computation no harder than the calculation of the 1-loop…

High Energy Physics - Phenomenology · Physics 2009-10-28 Mark Alford

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

Machine Learning · Computer Science 2026-02-03 Yuval Ran-Milo , Yotam Alexander , Shahar Mendel , Nadav Cohen

While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, residual policy learning (RPL)…

Robotics · Computer Science 2021-08-09 Alireza Ranjbar , Ngo Anh Vien , Hanna Ziesche , Joschka Boedecker , Gerhard Neumann

The Wilson loop with a wavy line contour is studied using integrable methods. The auxiliary problem is solved and the Lax operator is built to first order in perturbation theory, considering a small perturbation from the straight line.…

High Energy Physics - Theory · Physics 2013-12-30 A. Cagnazzo

Saliency maps are increasingly used as design guidance in siRNA efficacy prediction, yet attribution methods are rarely validated before motivating sequence edits. We introduce a pre-synthesis gate: a protocol for counterfactual sensitivity…

Genomics · Quantitative Biology 2026-03-09 Zahra Khodagholi , Niloofar Yousefi

We propose iterative inversion algorithms for weighted Radon transforms $R_W$ along hyperplanes in $R^3$. More precisely, expandingthe weight $W = W (x, \theta), x \in R^3 , \theta \in S^2$ , into the series of spherical harmonics in…

Mathematical Physics · Physics 2017-11-22 F Goncharov

Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without…

Machine Learning · Computer Science 2026-05-26 Rao Fu , Zixuan Yang , Jiankun Zhang , Jing Ma , Hechang Chen , Yu Li , Yi Chang

The standard prescription for computing Wilson loops in the AdS/CFT correspondence in the large coupling regime and tree-level involves minimizing the string action. In many cases the action has more than one saddle point as in the simple…

High Energy Physics - Theory · Physics 2010-02-03 Nadav Drukker

Wilson lines, being comparators that render non-local operator products gauge invariant, are extensively used in QCD calculations, especially in small-$x$ calculations, calculations concerning validation of factorisation schemes and in…

High Energy Physics - Phenomenology · Physics 2015-02-03 Frederik F. Van der Veken

One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic…

Machine Learning · Statistics 2026-03-24 Avrajit Ghosh , Bin Yu , Manfred Warmuth , Peter Bartlett
‹ Prev 1 2 3 10 Next ›