English
Related papers

Related papers: Compute as Teacher: Turning Inference Compute Into…

200 papers

Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods…

Machine Learning · Computer Science 2025-12-10 Jingyu Xing , Chenwei Tang , Xinyu Liu , Deng Xiong , Shudong Huang , Wei Ju , Jiancheng Lv , Ziyue Qiao

Answering questions about images often requires combining visual understanding with external knowledge. Multimodal Large Language Models (MLLMs) provide a natural framework for this setting, but they often struggle to identify the most…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Marco Morini , Sara Sarto , Marcella Cornia , Lorenzo Baraldi

Curriculum learning and imitation learning have been leveraged extensively in the robotics domain. However, minimal research has been done on leveraging these ideas on control tasks over highly stochastic time-series data. Here, we…

Machine Learning · Computer Science 2024-01-17 Woosung Koh , Insu Choi , Yuntae Jang , Gimin Kang , Woo Chang Kim

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Mehdi Noroozi , Ananth Vinjimoor , Paolo Favaro , Hamed Pirsiavash

Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since recursive and one-off…

In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning where a learning algorithm has access to a small set of labeled samples and a large set of unlabeled samples. Pseudo-labeling works by applying…

Machine Learning · Computer Science 2020-12-11 Paola Cascante-Bonilla , Fuwen Tan , Yanjun Qi , Vicente Ordonez

We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals…

Computation and Language · Computer Science 2021-09-13 Xiang Deng , Yu Su , Alyssa Lees , You Wu , Cong Yu , Huan Sun

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…

Information Retrieval · Computer Science 2026-04-10 Roxana Petcu , Evangelos Kanoulas , Maarten de Rijke

The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite the promise and some decent results, the existing AutoEval…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Ru Peng , Qiuyang Duan , Haobo Wang , Jiachen Ma , Yanbo Jiang , Yongjun Tu , Xiu Jiang , Junbo Zhao

Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a…

Computation and Language · Computer Science 2020-04-27 Alexander R. Fabbri , Patrick Ng , Zhiguo Wang , Ramesh Nallapati , Bing Xiang

Chain-of-Thought (CoT) is an efficient prompting method that enables the reasoning ability of large language models by augmenting the query using multiple examples with multiple intermediate steps. Despite the empirical success, the…

Machine Learning · Computer Science 2025-05-27 Hongkang Li , Songtao Lu , Pin-Yu Chen , Xiaodong Cui , Meng Wang

This paper explores the challenge of procedure planning in instructional videos, which involves creating goal-directed plans based on visual start and goal observations from videos. Previous research has tackled this problem with gradually…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Xinjie Li

Evaluating the trustworthiness of a model's prediction is essential for differentiating between `right for the right reasons' and `right for the wrong reasons'. Identifying textual spans that determine the target label, known as faithful…

Computation and Language · Computer Science 2020-10-08 Max Glockner , Ivan Habernal , Iryna Gurevych

Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches require ground-truth labels to seed or filter these traces -…

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Gustavo A. Vargas Hakim , David Osowiechi , Mehrdad Noori , Milad Cheraghalikhani , Ismail Ben Ayed , Christian Desrosiers

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

Machine Learning · Computer Science 2020-06-22 Samet Oymak , Talha Cihad Gulcu

Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive step-level annotations or ground truth references. We propose…

Machine Learning · Computer Science 2025-12-04 Salman Rahman , Sruthi Gorantla , Arpit Gupta , Swastik Roy , Nanyun Peng , Yang Liu

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

Machine Learning · Statistics 2026-02-03 Kento Kuwataka , Taiji Suzuki

In this paper, we propose a self-supervised learning procedure for training a robust multi-object tracking (MOT) model given only unlabeled video. While several self-supervisory learning signals have been proposed in prior work on…

Computer Vision and Pattern Recognition · Computer Science 2021-11-12 Favyen Bastani , Songtao He , Sam Madden

Scarcity of labeled data is a bottleneck for supervised learning models. A paradigm that has evolved for dealing with this problem is data programming. An existing data programming paradigm allows human supervision to be provided as a set…

Machine Learning · Computer Science 2019-11-25 Oishik Chatterjee , Ganesh Ramakrishnan , Sunita Sarawagi