English
Related papers

Related papers: Random Scaling of Emergent Capabilities

200 papers

Scaling laws for large language models (LLMs) predict model performance based on parameters like size and training data. However, differences in training configurations and data processing across model families lead to significant…

Machine Learning · Computer Science 2025-12-03 Felipe Maia Polo , Seamus Somerstep , Leshem Choshen , Yuekai Sun , Mikhail Yurochkin

With the rise of neural models across the field of information retrieval, numerous publications have incrementally pushed the envelope of performance for a multitude of IR tasks. However, these networks often sample data in random order,…

Information Retrieval · Computer Science 2018-06-12 Daniel Cohen , Scott M. Jordan , W. Bruce Croft

Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution…

Machine Learning · Computer Science 2021-02-09 Jens Müller , Robert Schmier , Lynton Ardizzone , Carsten Rother , Ullrich Köthe

A connection is made between the random turns model of vicious walkers and random permutations indexed by their increasing subsequences. Consequently the scaled distribution of the maximum displacements in a particular asymmeteric version…

Combinatorics · Mathematics 2007-05-23 P. J. Forrester

Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on…

Machine Learning · Statistics 2019-11-13 Julius Lauw , Dominique Macias , Akshay Trikha , Julia Vendemiatti , George D. Montanez

Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it effective across diverse application domains. However, the piecewise constant nature of…

Machine Learning · Computer Science 2026-05-19 Ziyi Liu , Phuc Luong , Mario Boley , Daniel F. Schmidt

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Computation and Language · Computer Science 2020-11-20 John Wieting , Graham Neubig , Taylor Berg-Kirkpatrick

Language models suffer from various degenerate behaviors. These differ between tasks: machine translation (MT) exhibits length bias, while tasks like story generation exhibit excessive repetition. Recent work has attributed the difference…

Computation and Language · Computer Science 2022-10-21 Darcey Riley , David Chiang

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-13 Santiago Cuervo , Ricard Marxer

In a range of scientific coauthorship networks, transitions emerge in degree distributions, correlations between degrees and local clustering coefficients, etc. The existence of those transitions could be regarded as a result of the…

Physics and Society · Physics 2018-06-19 Zheng Xie , Enming Dong , Dongyun Yi , Ouyang Zhenzheng , Jianping Li

The rapid advancement of large language model (LLM) technology has led to diverse applications, many of which inherently require randomness, such as stochastic decision-making, gaming, scheduling, AI agents, and cryptography-related tasks.…

Artificial Intelligence · Computer Science 2025-10-15 Rabimba Karanjai , Yang Lu , Ranjith Chodavarapu , Lei Xu , Weidong Shi

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are…

Scaling laws describe how language models improve with additional data, parameters, and compute. While widely used, they are typically measured on aggregate test sets. Aggregate evaluations yield clean trends but average over heterogeneous…

Computation and Language · Computer Science 2026-01-16 William Held , David Hall , Percy Liang , Diyi Yang

We investigate the scaling limit of the seed bank diffusion when reproduction and migration (to and from the seed bank) happen on different time-scales. More precisely, we consider the case when migration is `slow' and reproduction is…

We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute…

Machine Learning · Computer Science 2026-05-06 Khang Ngo , Siamak Ravanbakhsh

This work presents a new approach to decentralized training-SeedFlood-designed to scale for large models across complex network topologies and achieve global consensus with minimal communication overhead. Traditional gossip-based methods…

Machine Learning · Computer Science 2026-02-23 Jihun Kim , Namhoon Lee

Generative recommendation models can model user behavior as sequences of events and provide a shared backbone for multiple recommendation tasks. In production, however, pre-training gains do not automatically translate into downstream…

Information Retrieval · Computer Science 2026-05-25 Qiuling Xu , Ko-Jen Hsiao , Moumita Bhattacharya

A discrete binomial random-walk description of molecular collisions is used to quantify the variance of coarse-grained velocity fields arising solely from collision-induced momentum exchange. Closed-form expressions for the growth of…

Chemical Physics · Physics 2026-02-26 Tristan Barkman

Neural networks posses the crucial ability to generate meaningful representations of task-dependent features. Indeed, with appropriate scaling, supervised learning in neural networks can result in strong, task-dependent feature learning.…

Machine Learning · Computer Science 2025-05-13 Alexander van Meegen , Haim Sompolinsky

Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial…

Machine Learning · Computer Science 2024-10-15 Edwin Zhang , Vincent Zhu , Naomi Saphra , Anat Kleiman , Benjamin L. Edelman , Milind Tambe , Sham M. Kakade , Eran Malach