English
Related papers

Related papers: Universal Length Generalization with Turing Progra…

200 papers

Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small neural…

Machine Learning · Computer Science 2023-05-26 Bilal Chughtai , Lawrence Chan , Neel Nanda

Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps.…

Computation and Language · Computer Science 2024-07-12 Flavio Petruzzellis , Alberto Testolin , Alessandro Sperduti

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Machine Learning · Computer Science 2024-03-06 Suzan Ece Ada , Emre Ugur , H. Levent Akin

Learning to use tools to solve a variety of tasks is an innate ability of humans and has been observed of animals in the wild. However, the underlying mechanisms that are required to learn to use tools are abstract and widely contested in…

Neural and Evolutionary Computing · Computer Science 2019-07-04 Sam Wenke , Dan Saunders , Mike Qiu , Jim Fleming

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is…

Neural and Evolutionary Computing · Computer Science 2014-12-11 Alex Graves , Greg Wayne , Ivo Danihelka

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instructing the model to produce intermediate reasoning steps.…

Machine Learning · Computer Science 2025-03-03 Jianhao Huang , Zixuan Wang , Jason D. Lee

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

Computation and Language · Computer Science 2024-10-03 Wenzhen Zheng , Wenbo Pan , Xu Xu , Libo Qin , Li Yue , Ming Zhou

We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to…

Machine Learning · Computer Science 2020-07-09 Yujia Li , Felix Gimeno , Pushmeet Kohli , Oriol Vinyals

We introduce a new type of generalized Turing machines (GTMs), which are intended as a tool for the mathematician who studies computability in Analysis. In a single tape cell a GTM can store a symbol, a real number, a continuous real…

Logic · Mathematics 2015-07-01 Nazanin Tavana , Klaus Weihrauch

Recently, many techniques have been introduced that allow the (automated) classification of the runtime complexity of term rewrite systems (TRSs for short). In earlier work, the authors have shown that for confluent TRSs, innermost…

Computational Complexity · Computer Science 2011-06-09 Martin Avanzini , Georg Moser

Instruction tuning -- fine-tuning a large language model (LLM) on pairs of instructions and desired outcomes -- is an approach that enables pre-trained language models to perform real-world tasks and follow human instructions. Its practical…

Computation and Language · Computer Science 2024-02-19 Dylan Zhang , Justin Wang , Francois Charton

Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with complex tasks involving mathematics or reasoning. Despite the…

Machine Learning · Computer Science 2023-12-27 Guhao Feng , Bohang Zhang , Yuntian Gu , Haotian Ye , Di He , Liwei Wang

In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g.,…

Artificial Intelligence · Computer Science 2018-03-16 Danfei Xu , Suraj Nair , Yuke Zhu , Julian Gao , Animesh Garg , Li Fei-Fei , Silvio Savarese

Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems. While longer CoTs are often presumed superior, this paper challenges that notion, arguing that longer is not always better. Drawing on…

Artificial Intelligence · Computer Science 2025-05-28 Yuyang Wu , Yifei Wang , Ziyu Ye , Tianqi Du , Stefanie Jegelka , Yisen Wang

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design…

Machine Learning · Computer Science 2017-07-31 Carlo Ciliberto , Alessandro Rudi , Lorenzo Rosasco

Task-oriented grasping (TOG) is more challenging than simple object grasping because it requires precise identification of object parts and careful selection of grasping areas to ensure effective and robust manipulation. While recent…

Robotics · Computer Science 2026-03-30 Hao Chen , Takuya Kiyokawa , Weiwei Wan , Kensuke Harada

Task-oriented grasping (TOG) refers to the problem of predicting grasps on an object that enable subsequent manipulation tasks. To model the complex relationships between objects, tasks, and grasps, existing methods incorporate semantic…

Robotics · Computer Science 2023-09-21 Chao Tang , Dehao Huang , Wenqi Ge , Weiyu Liu , Hong Zhang

Utilizing tools with Large Language Models (LLMs) is essential for grounding AI agents in real-world applications. The prevailing approach involves few-shot prompting with demonstrations or fine-tuning with expert annotations. However, mere…

Computation and Language · Computer Science 2024-10-10 Xiaohan Wang , Dian Li , Yilin Zhao , Sinbadliu , Hui Wang

Machine learning explorations can make significant inroads into solving difficult problems in pure mathematics. One advantage of this approach is that mathematical datasets do not suffer from noise, but a challenge is the amount of data…

Machine Learning · Computer Science 2026-05-08 Max Petschack , Alexandr Garbali , Jan de Gier

A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a separate learner per task or training a single learner for all…

Machine Learning · Computer Science 2019-05-09 Michael B. Chang , Abhishek Gupta , Sergey Levine , Thomas L. Griffiths