English
Related papers

Related papers: Transformers Can Learn Rules They've Never Seen: P…

200 papers

Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine. However, Transformer models, while lacking recurrence, are able to perform such reasoning…

Machine Learning · Computer Science 2023-05-03 Bingbin Liu , Jordan T. Ash , Surbhi Goel , Akshay Krishnamurthy , Cyril Zhang

Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, they are still able to solve unseen tasks well purely based on…

Machine Learning · Computer Science 2024-11-19 Zihao Li , Yuan Cao , Cheng Gao , Yihan He , Han Liu , Jason M. Klusowski , Jianqing Fan , Mengdi Wang

We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025)…

Machine Learning · Computer Science 2025-11-03 Zachary Izzo , Eshaan Nichani , Jason D. Lee

Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the…

Machine Learning · Computer Science 2026-03-10 Ruipeng Zhang , Hongzhan Yu , Ya-Chien Chang , Chenghao Li , Henrik I. Christensen , Sicun Gao

We prove that transformers can exactly interpolate datasets of finite input sequences in $\mathbb{R}^d$, $d\geq 2$, with corresponding output sequences of smaller or equal length. Specifically, given $N$ sequences of arbitrary but finite…

Machine Learning · Computer Science 2026-05-14 Albert Alcalde , Giovanni Fantuzzi , Enrique Zuazua

Machine learning models can make critical errors that are easily hidden within vast amounts of data. Such errors often run counter to rules based on human intuition. However, rules based on human knowledge are challenging to scale or to…

Machine Learning · Computer Science 2023-06-08 Aaditya Naik , Yinjun Wu , Mayur Naik , Eric Wong

The transformer's remarkable ability to perform in-context learning (ICL) has sparked a wide range of studies designed to understand its strengths and limitations. However, a theoretical understanding of when ICL can and cannot generalize…

Machine Learning · Statistics 2026-04-30 Soo Min Kwon , Alec S. Xu , Can Yaras , Laura Balzano , Qing Qu

Model extrapolation to unseen flow is one of the biggest challenges facing data-driven turbulence modeling, especially for models with high dimensional inputs that involve many flow features. In this study we review previous efforts on…

Fluid Dynamics · Physics 2020-01-16 Shirui Luo , Jiahuan Cui , Madhu Vellakal , Jian Liu , Enyi Jiang , Seid Koric , Volodymyr Kindratenko

Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…

Machine Learning · Computer Science 2025-06-27 Tim Lawson , Laurence Aitchison

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

Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient…

The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these capabilities, Sanford et al. proposed the sparse token…

Machine Learning · Statistics 2024-06-12 Zixuan Wang , Stanley Wei , Daniel Hsu , Jason D. Lee

This paper reveals a novel linear characteristic exclusive to transformer decoders, including models such as GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations between sequential layers, uncovering a near-perfect linear…

Length extrapolation has attracted considerable attention recently since it allows transformers to be tested on longer sequences than those used in training. Previous research has shown that this property can be attained by using carefully…

Computation and Language · Computer Science 2023-12-20 Zhen Qin , Yiran Zhong , Hui Deng

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

Machine Learning · Computer Science 2020-11-12 Sudeep Dasari , Abhinav Gupta

Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing…

Machine Learning · Computer Science 2024-07-04 Yoav Wald , Gal Yona , Uri Shalit , Yair Carmon

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and the utility of its…

Computation and Language · Computer Science 2024-06-21 Alexander Yom Din , Taelin Karidi , Leshem Choshen , Mor Geva

The process of developing control functions for embedded systems is resource-, time-, and data-intensive, often resulting in sub-optimal cost and solutions approaches. Reinforcement Learning (RL) has great potential for autonomously…

Machine Learning · Computer Science 2025-03-06 Mario Picerno , Lucas Koch , Kevin Badalian , Marius Wegener , Joschka Schaub , Charles Robert Koch , Jakob Andert

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

Machine Learning · Computer Science 2026-01-15 Prudhviraj Naidu , Zixian Wang , Leon Bergen , Ramamohan Paturi

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently…

Machine Learning · Statistics 2025-01-14 Yihan He , Yuan Cao , Hong-Yu Chen , Dennis Wu , Jianqing Fan , Han Liu