English
Related papers

Related papers: LACE: Loss-Adaptive Capacity Expansion for Continu…

200 papers

In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Joshua Peeples , Connor McCurley , Sarah Walker , Dylan Stewart , Alina Zare

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a…

Machine Learning · Computer Science 2026-05-01 Aditya A. Ramesh , Alex Lewandowski , Jürgen Schmidhuber

Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and ideal pretext tasks for graph contrastive learning remains…

Machine Learning · Computer Science 2024-10-22 Zhenyu Lin , Hongzheng Li , Yingxia Shao , Guanhua Ye , Yawen Li , Quanqing Xu

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Artificial Intelligence · Computer Science 2026-04-08 Hangoo Kang , Tarun Suresh , Jon Saad-Falcon , Azalia Mirhoseini

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Xinyuan Gao , Songlin Dong , Yuhang He , Xing Wei , Yihong Gong

A major challenge in modern reinforcement learning (RL) is efficient control of dynamical systems from high-dimensional sensory observations. Learning controllable embedding (LCE) is a promising approach that addresses this challenge by…

Machine Learning · Computer Science 2020-06-25 Brandon Cui , Yinlam Chow , Mohammad Ghavamzadeh

Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization,…

Machine Learning · Computer Science 2023-07-13 Arnab Neelim Mazumder , Niall Lyons , Ashutosh Pandey , Avik Santra , Tinoosh Mohsenin

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Machine Learning · Computer Science 2023-12-22 Kamil Deja , Bartosz Cywiński , Jan Rybarczyk , Tomasz Trzciński

This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…

Machine Learning · Computer Science 2021-01-14 Matt Peng , Banghua Zhu , Jiantao Jiao

Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (SSL) backbones encode rich inter-class semantics of general objects, we show they fail to…

Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the same redundant ways. We introduce LACE, a framework that…

Artificial Intelligence · Computer Science 2026-05-12 Yang Li , Zirui Zhang , Yang Liu , Chengzhi Mao

We revisit continual pre-training for large language models and argue that progress now depends more on scaling the right structure than on scaling parameters alone. We introduce SCALE, a width upscaling architecture that inserts…

Computation and Language · Computer Science 2025-12-12 Jin-woo Lee , Junhwa Choi , Bongkyu Hwang , Jinho Choo , Bogun Kim , JeongSeon Yi , Joonseok Lee , DongYoung Jung , Jaeseon Park , Kyoungwon Park , Suk-hoon Jung

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Qiang Meng , Chixiang Zhang , Xiaoqiang Xu , Feng Zhou

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

Machine Learning · Computer Science 2021-02-04 Gobinda Saha , Isha Garg , Aayush Ankit , Kaushik Roy

Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing…

Computation and Language · Computer Science 2025-09-23 Ali Veisi , Hamidreza Amirzadeh , Amir Mansourian

We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key…

Machine Learning · Computer Science 2026-02-04 Romain Cosentino

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Wentao Zhang , Yujun Huang , Tong Zhang , Qingsong Zou , Wei-Shi Zheng , Ruixuan Wang

To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for…

Robotics · Computer Science 2026-05-18 Ralf Römer , Yi Zhang , Yuming Li , Angela P. Schoellig

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

We introduce Learning-Augmented Control (LAC), an approach that integrates untrusted machine learning predictions into the control of constrained, nonlinear dynamical systems. LAC is designed to achieve the "best-of-both-worlds" guarantees,…

Systems and Control · Electrical Eng. & Systems 2025-07-22 Tongxin Li
‹ Prev 1 2 3 10 Next ›