CL
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
arXiv:2605.19145v2 Announce Type: replace Abstract: In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all CL approaches use some form of memory to retain information about past tasks, a grounded understanding of what information needs to be stored to minimize catastrophic forgetting remains elusive....
CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning
arXiv:2606.02659v1 Announce Type: new Abstract: Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patterns, thereby enhancing data processing and decision-making. While existing methods for structured multimodal inputs are typically designed around specific tasks and assume fully observed modalities, real-world applications often suffer from uncertain or missing modality inputs due to various...
CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
arXiv:2606.06978v1 Announce Type: new Abstract: Continual Object Detection (COD) requires a detector to acquire new categories over time while preserving previously learned ones. This goal is closely related to open-vocabulary detection, since both settings require reasoning over categories that are not fully covered by the annotations available at the current training stage. Recent CLIP-based open-vocabulary detectors have shown strong zero-shot generalization, and frameworks such as F-ViT...
'It'll be suicidal': Robin on tactical battle that could decide PSG vs Arsenal in CL Final
PSG carry the weight of champions, refusing to stop as they hope to retain the crown. Arsenal arrive with carpe diem in their hearts and history at their backs as they find themselves in the final of the Champions League for the first time since 2006. And if Arsenal get over the line, they would also become only the 25th club to ever win the European Cup or Champions League, having played 225 games in the competition - more than any other club to have never lifted the trophy.
Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learning
Announce Type: replace Abstract: In Continual Learning (CL), using a Pre-Trained Model (PTM) as the feature extractor has become a popular practice. Accompanied by analytic classifiers, the PTM-based methods have achieved state-of-the-art performance in CL, in pursuit of the non-forgetting goal. Meanwhile, actively forgetting specific knowledge acquired during the CL phase is also essential in most service construction paradigms, for example, Mobile Crowd Sensing (MCS), where mobile edge...
Theoretical Foundations of Continual Learning via Drift-Plus-Penalty
arXiv:2606.08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch. Continual learning (CL) addresses this challenge by incorporating new tasks while mitigating catastrophic forgetting, where learning new information degrades performance on previously acquired knowledge. We introduce a control-theoretic perspective on CL that explicitly regulates...
PURGE: Projected Unlearning via Retain-Guided Erasure
arXiv:2606.03808v1 Announce Type: new Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems. CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions. PURGE leverages this duality by adapting gradient projection...
Consistent Distributed Cooperative Localization for Ultra Large-Scale Multi-agent Systems
arXiv:2606.04872v1 Announce Type: new Abstract: Cooperative localization (CL) is fundamental in emerging multi-agent systems, where agents fuse local sensing data with exchanged information to estimate their own states. At a large scale, however, tracking cross-correlations becomes infeasible, preventing the use of optimal filters. Ignoring or underestimating these correlations leads to overconfident, and thus inconsistent, estimates.
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
arXiv:2605.24863v2 Announce Type: replace-cross Abstract: Speech and audio systems operate in inherently non-stationary environments, yet continual learning (CL) research in this domain, especially in the foundation model era, remains fragmented that fail to account for the coupled, geometry-sensitive nature of acoustic representations. Modern speech foundation models operate over highly entangled, continuous representations that jointly encode linguistic, speaker, and paralinguistic factors...
Fast Transformer Inference on ARM-Based HMPSoCs
arXiv:2606.02836v1 Announce Type: new Abstract: Transformer models have set new performance standards for machine learning (ML) tasks. However, their resource-intensive deployment on resource-constrained edge devices for cloud-free, on-chip transformer inference remains challenging. The ARM Compute Library (ARM-CL) framework provides low-latency CNN inference on ARM-based edge devices but lacks support for transformer inference.