English
Related papers

Related papers: Heuristic Transformer: Belief Augmented In-Context…

200 papers

Reinforcement learning (RL) agents often struggle to generalize to new tasks and contexts without updating their parameters, mainly because their learned representations and policies are overfit to the specifics of their training…

Machine Learning · Computer Science 2025-08-12 Fernando Martinez-Lopez , Tao Li , Yingdong Lu , Juntao Chen

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We…

Computation and Language · Computer Science 2026-05-27 Yiran Huang , Karsten Roth , Quentin Bouniot , Wenjia Xu , Zeynep Akata

A striking property of transformers is their ability to perform in-context learning (ICL), a machine learning framework in which the learner is presented with a novel context during inference implicitly through some data, and tasked with…

Machine Learning · Computer Science 2024-05-29 Liam Collins , Advait Parulekar , Aryan Mokhtari , Sujay Sanghavi , Sanjay Shakkottai

Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational…

Artificial Intelligence · Computer Science 2026-04-16 Shuai Zhen , Yanhua Yu , Ruopei Guo , Nan Cheng , Yang Deng

In this paper, we propose a hierarchical contrastive learning framework, HiCL, which considers local segment-level and global sequence-level relationships to improve training efficiency and effectiveness. Traditional methods typically…

Computation and Language · Computer Science 2023-10-17 Zhuofeng Wu , Chaowei Xiao , VG Vinod Vydiswaran

Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently…

Machine Learning · Computer Science 2023-05-24 Chenyang Zhao , Zihao Zhou , Bin Liu

Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an…

Machine Learning · Computer Science 2025-08-08 Arik Reuter , Tim G. J. Rudner , Vincent Fortuin , David Rügamer

Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-scaling, where model…

Machine Learning · Computer Science 2024-10-17 Amirhesam Abedsoltan , Adityanarayanan Radhakrishnan , Jingfeng Wu , Mikhail Belkin

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of…

Machine Learning · Computer Science 2019-08-19 Daniel S. Brown , Scott Niekum

In-context learning (ICL) has emerged as a powerful paradigm for easily adapting Large Language Models (LLMs) to various tasks. However, our understanding of how ICL works remains limited. We explore a simple model of ICL in a controlled…

Machine Learning · Computer Science 2025-09-03 Omar Naim , Guilhem Fouilhé , Nicholas Asher

Attention-based neural networks such as transformers have demonstrated a remarkable ability to exhibit in-context learning (ICL): Given a short prompt sequence of tokens from an unseen task, they can formulate relevant per-token and…

Machine Learning · Statistics 2023-10-23 Ruiqi Zhang , Spencer Frei , Peter L. Bartlett

Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent…

Artificial Intelligence · Computer Science 2026-03-23 Wenjian Zhang , Kongcheng Zhang , Jiaxin Qi , Baisheng Lai , Jianqiang Huang

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning…

Machine Learning · Computer Science 2021-12-07 Nico Gürtler , Dieter Büchler , Georg Martius

The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be…

Machine Learning · Computer Science 2022-06-14 Kushal Chauhan , Soumya Chatterjee , Akash Reddy , Balaraman Ravindran , Pradeep Shenoy

In-context learning (ICL) has garnered significant attention for its ability to grasp functions/tasks from demonstrations. Recent studies suggest the presence of a latent task/function vector in LLMs during ICL. Merullo et al. (2024) showed…

Machine Learning · Computer Science 2025-08-14 Dake Bu , Wei Huang , Andi Han , Atsushi Nitanda , Qingfu Zhang , Hau-San Wong , Taiji Suzuki

Transformer models exhibit in-context learning: the ability to accurately predict the response to a novel query based on illustrative examples in the input sequence. In-context learning contrasts with traditional in-weights learning of…

Machine Learning · Computer Science 2023-12-07 Gautam Reddy

In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios:…

Machine Learning · Computer Science 2025-10-03 Hadi Askari , Shivanshu Gupta , Terry Tong , Fei Wang , Anshuman Chhabra , Muhao Chen

Reinforcement learning in complex environments is a challenging problem. In particular, the success of reinforcement learning algorithms depends on a well-designed reward function. Inverse reinforcement learning (IRL) solves the problem of…

Machine Learning · Computer Science 2021-01-20 Rakhoon Hwang , Hanjin Lee , Hyung Ju Hwang

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

Disordered Systems and Neural Networks · Physics 2026-04-24 Kaito Takanami , Takashi Takahashi , Yoshiyuki Kabashima

Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a…

Machine Learning · Statistics 2025-10-06 Yue M. Lu , Mary I. Letey , Jacob A. Zavatone-Veth , Anindita Maiti , Cengiz Pehlevan