Copertina

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Alssum, Lama, Hammoud, Hasan Abed Al Kader, Alfarra, Motasem, Alcazar, Juan C Leon, Ghanem, Bernard
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DiffCLIP: Differential Attention Meets CLIP
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
di: Alssum, Lama, et al.
Pubblicazione: (2025)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models
di: Villa, Andrés, et al.
Pubblicazione: (2025)

Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos
di: Ramazanova, Merey, et al.
Pubblicazione: (2024)

SimCS: Simulation for Domain Incremental Online Continual Segmentation
di: Alfarra, Motasem, et al.
Pubblicazione: (2022)

On the Importance of Pretraining Data Alignment for Atomic Property Prediction
di: Ghunaim, Yasir, et al.
Pubblicazione: (2025)

Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
di: Zbeeb, Mohammad, et al.
Pubblicazione: (2025)

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
di: Alhuwaider, Shyma, et al.
Pubblicazione: (2025)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
di: Shairah, Harethah Abu, et al.
Pubblicazione: (2025)

On Pretraining Data Diversity for Self-Supervised Learning
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2024)

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2024)

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
di: Yang, Yibo, et al.
Pubblicazione: (2024)

Online Distillation with Continual Learning for Cyclic Domain Shifts
di: Houyon, Joachim, et al.
Pubblicazione: (2023)

An Embarrassingly Simple Defense Against LLM Abliteration Attacks
di: Shairah, Harethah Abu, et al.
Pubblicazione: (2025)

Deep Learning at the Intersection: Certified Robustness as a Tool for 3D Vision
di: S, Gabriel Pérez, et al.
Pubblicazione: (2024)

TAPS: Task Aware Proposal Distributions for Speculative Sampling
di: Zbib, Mohamad, et al.
Pubblicazione: (2026)

From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
di: Prabhu, Ameya, et al.
Pubblicazione: (2023)

Towards Faster and More Compact Foundation Models for Molecular Property Prediction
di: Ghunaim, Yasir, et al.
Pubblicazione: (2025)

FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
di: Alhamoud, Kumail, et al.
Pubblicazione: (2024)

OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
di: Liu, Shuming, et al.
Pubblicazione: (2025)

Evaluation of Test-Time Adaptation Under Computational Time Constraints
di: Alfarra, Motasem, et al.
Pubblicazione: (2023)

Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning
di: Chen, Haoran, et al.
Pubblicazione: (2025)

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2024)

Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning
di: Tamajo, Alberto, et al.
Pubblicazione: (2026)

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
di: Slim, Ali, et al.
Pubblicazione: (2026)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
di: Rezaei, Hossein, et al.
Pubblicazione: (2024)

Less Is More: An Explainable AI Framework for Lightweight Malaria Classification
di: Kafi, Md Abdullah Al, et al.
Pubblicazione: (2025)

Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models
di: Villa, Andrés, et al.
Pubblicazione: (2023)

MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
di: Zhang, Tong, et al.
Pubblicazione: (2025)

AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
di: Zbeeb, Mohammad, et al.
Pubblicazione: (2025)

Reinforcement Learning, Optimal Control, and Bayesian Filtering in Data Assimilation
di: Hammoud, Abed
Pubblicazione: (2026)

Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration
di: Pérez, Juan C., et al.
Pubblicazione: (2024)

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
di: Yang, Yibo, et al.
Pubblicazione: (2025)

MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs
di: Barrios, Wayner, et al.
Pubblicazione: (2025)

Hierarchical Prompts for Rehearsal-free Continual Learning
di: Zuo, Yukun, et al.
Pubblicazione: (2024)

Consistent Prompting for Rehearsal-Free Continual Learning
di: Gao, Zhanxin, et al.
Pubblicazione: (2024)

Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning
di: Gao, Xinyuan, et al.
Pubblicazione: (2024)