English
Related papers

Related papers: When perceptual time stands still: Long stable mem…

200 papers

On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

Machine Learning · Computer Science 2026-04-16 Yaxuan Li , Yuxin Zuo , Bingxiang He , Jinqian Zhang , Chaojun Xiao , Cheng Qian , Tianyu Yu , Huan-ang Gao , Wenkai Yang , Zhiyuan Liu , Ning Ding

It is often of interest to study the association between covariates and the cumulative incidence of a right-censored time-to-event outcome. When time-varying covariates are measured on a fixed discrete time scale, it is desirable to account…

Methodology · Statistics 2026-04-28 Hongxiang Qiu , Marco Carone , Alex Luedtke , Peter B. Gilbert

In Partially Observable Markov Decision Processes, integrating an agent's history into memory poses a significant challenge for decision-making. Traditional imitation learning, relying on observation-action pairs for expert demonstrations,…

Machine Learning · Computer Science 2024-11-14 William Yue , Bo Liu , Peter Stone

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, outside of restrictive…

Machine Learning · Computer Science 2024-10-24 Philip Amortila , Dylan J. Foster , Nan Jiang , Akshay Krishnamurthy , Zakaria Mhammedi

Winner-take-all phenomena are observed in various competitive systems. We find similar phenomena in replicator models with randomly fluctuating growth rates. The disparity between winners and losers increases indefinitely, even if all…

Physics and Society · Physics 2016-03-23 Hidetsugu Sakaguchi

In this work we propose a new class of long-memory models with time-varying fractional parameter. In particular, the dynamics of the long-memory coefficient, $d$, is specified through a stochastic recurrence equation driven by the score of…

Methodology · Statistics 2018-12-19 Luisa Bisaglia , Matteo Grigoletto

We investigate how confinement may drastically change both the probability density of the first-encounter time and the related survival probability in the case of two diffusing particles. To obtain analytical insights into this problem, we…

Statistical Mechanics · Physics 2020-09-16 F. Le Vot , S. B. Yuste , E. Abad , D. S. Grebenkov

We establish sufficient conditions on durations that are stationary with finite variance and memory parameter $d \in [0,1/2)$ to ensure that the corresponding counting process $N(t)$ satisfies $\textmd{Var} N(t) \sim C t^{2d+1}$ ($C>0$) as…

Statistics Theory · Mathematics 2012-09-19 Rohit Deo , Clifford M. Hurvich , Philippe Soulier , Yi Wang

Human social life is shaped by repeated interactions, where past experiences guide future behavior. In evolutionary game theory, a key challenge is to identify strategies that harness such memory to succeed in repeated encounters. Decades…

Populations and Evolution · Quantitative Biology 2025-09-16 Ketian Sun , Qi Su , Long Wang

This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb…

Probability · Mathematics 2024-10-28 Gleb Smirnov

Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and…

Machine Learning · Computer Science 2024-09-04 Mark Bedaywi , Amin Rakhsha , Amir-massoud Farahmand

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training…

Computer Vision and Pattern Recognition · Computer Science 2020-09-16 Wei Hu , QiHao Zhao , Yangyu Huang , Fan Zhang

It is well-known that wave-type equations with memory, under appropriate assumptions on the memory kernel, are uniformly exponentially stable. On the other hand, time delay effects may destroy this behavior. Here, we consider the…

Analysis of PDEs · Mathematics 2015-07-14 Cristina Pignotti

This article underlines the learning and discrimination capabilities of a model of associative memory based on artificial networks of spiking neurons. Inspired from neuropsychology and neurobiology, the model implements top-down…

Neural and Evolutionary Computing · Computer Science 2016-08-16 Anthony Mouraud , Hélène Paugam-Moisy

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches…

Computation and Language · Computer Science 2025-06-12 Zikai Xiao , Ziyang Wang , Wen Ma , Yan Zhang , Wei Shen , Yan Wang , Luqi Gong , Zuozhu Liu

Memory plays a vital role in the temporal evolution of interactions of complex systems. To address the impact of memory on the temporal pattern of networks, we propose a simple preferential connection model, in which nodes have a…

Physics and Society · Physics 2020-01-16 F. Rabbani , T. Khraisha , F. Abbasi , G. R. Jafari

Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…

Artificial Intelligence · Computer Science 2026-05-22 Bingjun Luo , Tony Wang , Chaoqi Chen , Xinpeng Ding

Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the…

Machine Learning · Computer Science 2024-05-28 Hyunin Lee , Ming Jin , Javad Lavaei , Somayeh Sojoudi

Repeated interaction between individuals is the main mechanism for maintaining cooperation in social dilemma situations. Variants of tit-for-tat (repeating the previous action of the opponent) and the win-stay lose-shift strategy are known…

Populations and Evolution · Quantitative Biology 2011-11-08 Shoma Tanabe , Naoki Masuda

We want to understand the human capabilities to perceive amplitude similarities between a haptic and an audio signal. So, four psychophysical experiments were performed. Three of them measured the asynchrony JND (Just Noticeable Difference)…

Human-Computer Interaction · Computer Science 2020-03-18 Alfonso Balandra , Shoichi Hasegawa