English
Related papers

Related papers: Towards Monotonic Improvement in In-Context Reinfo…

200 papers

Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts,…

Machine Learning · Computer Science 2026-05-26 Minjae Kwon , Amir Moeini , Shangtong Zhang , Lu Feng

Bimodal software analysis initially appeared to be within reach with the advent of large language models. Unfortunately, the complex interplay of natural language text and code in software engineering, presents unique challenges that…

Software Engineering · Computer Science 2024-10-25 Xunzhu Tang , Liran Wang , Yonghui Liu , Linzheng Chai , Jian Yang , Zhoujun Li , Haoye Tian , Jacques Klein , Tegawende F. Bissyande

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical…

Machine Learning · Statistics 2024-10-03 Juno Kim , Tai Nakamaki , Taiji Suzuki

Large language models (LLMs) can adapt to new tasks via in-context learning (ICL) without parameter updates, making them powerful learning engines for fast adaptation. While extensive research has examined ICL as a few-shot learner, whether…

Machine Learning · Computer Science 2025-09-30 Liuwang Kang , Fan Wang , Shaoshan Liu , Hung-Chyun Chou , Chuan Lin , Ning Ding

Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden "trap states" --…

Machine Learning · Computer Science 2025-05-23 Yuxuan Li , Yicheng Gao , Ning Yang , Stephen Xia

This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates…

Machine Learning · Statistics 2025-12-09 Tomoya Wakayama , Taiji Suzuki

Leveraging temporal context is crucial for success in partially observable robotic tasks. However, prior work in behavior cloning has demonstrated inconsistent performance gains when using multi-frame observations. In this paper, we…

Robotics · Computer Science 2025-10-07 Huiwon Jang , Sihyun Yu , Heeseung Kwon , Hojin Jeon , Younggyo Seo , Jinwoo Shin

Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation…

Artificial Intelligence · Computer Science 2026-02-04 Qixin Zeng , Shuo Zhang , Hongyin Zhang , Renjie Wang , Han Zhao , Libang Zhao , Runze Li , Donglin Wang , Chao Huang

Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inadequate for capturing the compositional structure of tasks…

Machine Learning · Computer Science 2026-03-19 Qiushui Xu , Yuhao Huang , Yushu Jiang , Lei Song , Jinyu Wang , Wenliang Zheng , Jiang Bian

The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with…

Machine Learning · Computer Science 2026-03-02 Fan Wang , Zhiyuan Chen , Yuxuan Zhong , Sunjian Zheng , Pengtao Shao , Bo Yu , Shaoshan Liu , Jianan Wang , Ning Ding , Yang Cao , Yu Kang

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of language models (LLMs) without fine-tuning model parameters. While prompt-based adaptation techniques have demonstrated the…

Computation and Language · Computer Science 2025-11-04 Jack Lu , Ryan Teehan , Zhenbang Yang , Mengye Ren

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot…

Computation and Language · Computer Science 2024-04-30 Guozheng Li , Peng Wang , Jiajun Liu , Yikai Guo , Ke Ji , Ziyu Shang , Zijie Xu

Retrieval-Augmented Generation (RAG) addresses large language model (LLM) hallucinations by grounding responses in external knowledge, but its effectiveness is compromised by poor-quality retrieved contexts containing irrelevant or noisy…

Computation and Language · Computer Science 2025-10-27 Jiale Deng , Yanyan Shen , Ziyuan Pei , Youmin Chen , Linpeng Huang

This paper investigates the expected excess risk of in-context learning (ICL) for multiclass classification. We formalize each task as a sequence of labeled examples followed by a query input; a pretrained model then estimates the query's…

Machine Learning · Statistics 2025-09-03 Chenrui Liu , Falong Tan , Chuanlong Xie , Yicheng Zeng , Lixing Zhu

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…

Machine Learning · Computer Science 2021-01-05 Baiming Chen , Zuxin Liu , Jiacheng Zhu , Mengdi Xu , Wenhao Ding , Ding Zhao

Recently, the mysterious In-Context Learning (ICL) ability exhibited by Transformer architectures, especially in large language models (LLMs), has sparked significant research interest. However, the resilience of Transformers' in-context…

Computation and Language · Computer Science 2024-05-02 Chen Cheng , Xinzhi Yu , Haodong Wen , Jingsong Sun , Guanzhang Yue , Yihao Zhang , Zeming Wei

Demonstration ordering, which is an important strategy for in-context learning (ICL), can significantly affects the performance of large language models (LLMs). However, most of the current approaches of ordering require high computational…

Computation and Language · Computer Science 2024-06-18 Yinpeng Liu , Jiawei Liu , Xiang Shi , Qikai Cheng , Yong Huang , Wei Lu

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Yanshu Li , Jianjiang Yang , Ziteng Yang , Bozheng Li , Ligong Han , Hongyang He , Zhengtao Yao , Yingjie Victor Chen , Songlin Fei , Dongfang Liu , Ruixiang Tang

Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert. Many algorithms for IRL have an inherently nested…

Machine Learning · Computer Science 2022-11-02 Siliang Zeng , Chenliang Li , Alfredo Garcia , Mingyi Hong

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…

Computation and Language · Computer Science 2025-09-30 Hakaze Cho , Peng Luo , Mariko Kato , Rin Kaenbyou , Naoya Inoue