English
Related papers

Related papers: Composing Task Knowledge with Modular Successor Fe…

200 papers

We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale. By training a diffusion…

Chemical Physics · Physics 2024-05-13 Yuyang Wang , Ahmed A. Elhag , Navdeep Jaitly , Joshua M. Susskind , Miguel Angel Bautista

Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the…

Robotics · Computer Science 2025-02-14 Vivek Myers , Bill Chunyuan Zheng , Anca Dragan , Kuan Fang , Sergey Levine

The Cut posterior and related Semi-Modular Inference are Generalised Bayes methods for Modular Bayesian evidence combination. Analysis is broken up over modular sub-models of the joint posterior distribution. Model-misspecification in…

Machine Learning · Statistics 2022-04-04 Chris U. Carmona , Geoff K. Nicholls

Transfer in reinforcement learning is usually achieved through generalisation across tasks. Whilst many studies have investigated transferring knowledge when the reward function changes, they have assumed that the dynamics of the…

Machine Learning · Computer Science 2021-07-20 Majid Abdolshah , Hung Le , Thommen Karimpanal George , Sunil Gupta , Santu Rana , Svetha Venkatesh

Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/storage of their huge amount of parameters, which becomes…

Computer Vision and Pattern Recognition · Computer Science 2023-10-04 Xueqing Deng , Qi Fan , Xiaojie Jin , Linjie Yang , Peng Wang

While large language models (LLMs) have achieved impressive performance in generating fluent and realistic text, controlling the generated text so that it exhibits properties such as safety, factuality, and non-toxicity remains challenging.…

Computation and Language · Computer Science 2023-11-10 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

Predictive learning uses a known state to generate a future state over a period of time. It is a challenging task to predict spatiotemporal sequence because the spatiotemporal sequence varies both in time and space. The mainstream method is…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Haoyu Pan , Hao Wu , Tan Yang

To address the dual challenges of inherent stochasticity and non-differentiable metrics in physical spatiotemporal forecasting, we propose Spatiotemporal Forecasting as Planning (SFP), a new paradigm grounded in Model-Based Reinforcement…

Machine Learning · Computer Science 2025-10-13 Hao Wu , Yuan Gao , Xingjian Shi , Shuaipeng Li , Fan Xu , Fan Zhang , Zhihong Zhu , Weiyan Wang , Xiao Luo , Kun Wang , Xian Wu , Xiaomeng Huang

Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions…

Machine Learning · Computer Science 2026-05-14 Stefan Stojanovic , Alexandre Proutiere

Continual learning in neural networks aims to learn new tasks without forgetting old tasks. Sequential function-space variational inference (SFSVI) uses a Gaussian variational distribution to approximate the distribution of the outputs of…

Machine Learning · Computer Science 2025-05-28 Menghao Waiyan William Zhu , Pengcheng Hao , Ercan Engin Kuruoğlu

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form…

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Yongxi Lu , Abhishek Kumar , Shuangfei Zhai , Yu Cheng , Tara Javidi , Rogerio Feris

Machine learning classifiers' capability is largely dependent on the scale of available training data and limited by the model overfitting in data-scarce learning tasks. To address this problem, this work proposes a novel framework of Meta…

Machine Learning · Computer Science 2022-03-29 Pan Li , Yanwei Fu , Shaogang Gong

Sample efficiency is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can…

Machine Learning · Computer Science 2024-07-23 Parvin Malekzadeh , Ming Hou , Konstantinos N. Plataniotis

Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities.…

Machine Learning · Computer Science 2023-10-31 Siyan Zhao , Aditya Grover

Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at inference time, a policy sequentially chooses which features to acquire (at a cost) before predicting. Existing approaches either train reinforcement learning…

Artificial Intelligence · Computer Science 2026-02-05 Hung-Tien Huang , Dzung Dinh , Junier B. Oliva

The successor representation (SR) provides a powerful framework for decoupling predictive dynamics from rewards, enabling rapid generalisation across reward configurations. However, the classical SR is limited by its inherent policy…

Machine Learning · Computer Science 2026-02-16 Changmin Yu , Máté Lengyel

Classifier models are prevalent in natural language processing (NLP), often with high accuracy. Yet in real world settings, human-in-the-loop systems can foster trust in model outputs and even higher performance. Selective Prediction (SP)…

Computation and Language · Computer Science 2024-11-01 Zhaohui Li , Rebecca J. Passonneau

Trajectory prediction modules are key enablers for safe and efficient planning of autonomous vehicles (AVs), particularly in highly interactive traffic scenarios. Recently, learning-based trajectory predictors have experienced considerable…

Robotics · Computer Science 2023-07-06 Sushant Veer , Apoorva Sharma , Marco Pavone

Multi-task and few-shot time series forecasting tasks are commonly encountered in scenarios such as the launch of new products in different cities. However, traditional time series forecasting methods suffer from insufficient historical…

Machine Learning · Computer Science 2025-06-25 Pengpeng Ouyang , Dong Chen , Tong Yang , Shuo Feng , Zhao Jin , Mingliang Xu