English
Related papers

Related papers: Teacher Forcing as Generalized Bayes: Optimization…

200 papers

Inverse Constraint Learning (ICL) is the problem of inferring constraints from safe (i.e., constraint-satisfying) demonstrations. The hope is that these inferred constraints can then be used downstream to search for safe policies for new…

Robotics · Computer Science 2025-08-05 Mohamad Qadri , Gokul Swamy , Jonathan Francis , Michael Kaess , Andrea Bajcsy

Image-language models with prompt learning have shown remarkable advances in numerous downstream vision tasks. Nevertheless, conventional prompt learning methods overfit their training distribution and lose the generalization ability on…

Computer Vision and Pattern Recognition · Computer Science 2024-02-16 Zehao Xiao , Jiayi Shen , Mohammad Mahdi Derakhshani , Shengcai Liao , Cees G. M. Snoek

Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during…

Machine Learning · Computer Science 2026-02-23 Di Zhang

Clinical time-series learning is routinely constrained by small, heterogeneous cohorts and protocol drift, while its downstream use spans both classification (e.g., pathology diagnosis) and regression (e.g., temporal forecasting). These…

Machine Learning · Computer Science 2026-05-29 Sharmita Dey , Diego Paez-Granados

Language models (LMs) are often adapted through supervised fine-tuning (SFT) to specialize their capabilities for downstream tasks. However, in typical scenarios where the fine-tuning data is limited, e.g., compared to pre-training, SFT can…

Machine Learning · Computer Science 2025-11-18 Yunhun Nam , Jaehyung Kim , Jongheon Jeong

We investigate the ability of transformers to perform in-context reinforcement learning (ICRL), where a model must infer and execute learning algorithms from trajectory data without parameter updates. We show that a linear self-attention…

Machine Learning · Statistics 2026-05-08 Haodong Liang , Lifeng Lai

We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to…

Machine Learning · Computer Science 2025-12-08 Zachary Coalson , Juhan Bae , Nicholas Carlini , Sanghyun Hong

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important…

Machine Learning · Statistics 2021-10-29 Cassidy Laidlaw , Stuart Russell

Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overfitting, i.e., the robustness will drop sharply at a certain…

Machine Learning · Computer Science 2022-05-25 Shudong Zhang , Haichang Gao , Tianwei Zhang , Yunyi Zhou , Zihui Wu

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic…

Machine Learning · Computer Science 2026-05-27 Taesun Yeom , Taehyeok Ha , Jaeho Lee

Can a mere next-token predictor faithfully model human intelligence? We crystallize this emerging concern and correct popular misconceptions surrounding it, and advocate a simple multi-token objective. As a starting point, we argue that the…

Computation and Language · Computer Science 2025-07-30 Gregor Bachmann , Vaishnavh Nagarajan

The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass. While efficient, this rigid coupling of output and…

Machine Learning · Computer Science 2026-02-03 Jiaming Ma , Siyuan Mu , Ruilin Tang , Haofeng Ma , Qihe Huang , Zhengyang Zhou , Pengkun Wang , Binwu Wang , Yang Wang

This paper proposes a robust control strategy that integrates Iterative Learning Control (ILC) with a simple lateral neural network to enhance the trajectory tracking performance of a linear Lorentz force actuator under friction and model…

Systems and Control · Electrical Eng. & Systems 2025-11-18 Ali Mashhadireza , Ali Sadighi

Despite the massive success of fine-tuning Pre-trained Language Models (PLMs), they remain susceptible to out-of-distribution input. Dataset cartography is a simple yet effective dual-model approach that improves the robustness of…

Computation and Language · Computer Science 2024-12-12 Yupei Du , Albert Gatt , Dong Nguyen

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose…

Machine Learning · Computer Science 2026-01-08 Jingrui Zhang , Yimeng Xu , Shujie Li , Feng Liang , Haihan Duan , Yanjie Dong , Victor C. M. Leung , Xiping Hu

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this…

Machine Learning · Statistics 2022-10-18 Debarghya Mukherjee , Felix Petersen , Mikhail Yurochkin , Yuekai Sun

Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions. Despite its usefulness, the problem remains challenging due to the influences from noisy and outlier…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Zi Jian Yew , Gim Hee Lee

Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussian i.i.d. input data underlying the canonical teacher-student…

Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption (TTA) continues to adapt the model after deployment. Recently, the area of continual and gradual test-time adaptation (TTA) emerged. In contrast…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Mario Döbler , Robert A. Marsden , Bin Yang

Learning governing dynamics from data is a common goal across the sciences, yet it is only well-posed when the underlying mechanisms are identifiable. In practice, many data-driven methods implicitly assume identifiability; when this…

Machine Learning · Computer Science 2026-05-13 Aybüke Ulusarslan , Niki Kilbertus , Nora Schneider
‹ Prev 1 8 9 10 Next ›