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

Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that…

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-stationary problem settings. Recent work has shown that deep…

Access control in the Internet of Things (IoT) is becoming increasingly complex, as policies must account for dynamic and contextual factors such as time, location, user behavior, and environmental conditions. However, existing platforms…

With the development of deep learning, the field of face anti-spoofing (FAS) has witnessed great progress. FAS is usually considered a classification problem, where each class is assumed to contain a single cluster optimized by softmax…

Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where environment dynamics may differ. A key challenge is to leverage source data while reducing…

Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting problem.…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Large language models (LLMs) have become a central foundation of modern artificial intelligence, yet their lifecycle remains constrained by a rigid separation between training and deployment, after which learning effectively ceases. This…

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that…

We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1)…

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

Federated unlearning (FU) aims to erase designated client-level, class-level, or sample-level knowledge from a global model. Existing studies commonly assume that the collaboration ends up with the unlearning operation, overlooking the…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

Deep Learning (DL) training platforms are built by interconnecting multiple DL accelerators (e.g., GPU/TPU) via fast, customized interconnects with 100s of gigabytes (GBs) of bandwidth. However, as we identify in this work, driving this…

Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are…

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply…

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…