The Geometry of Forgetting: A Fisher-Information Framework for Alignment-Preserving Continual Adaptation
Aligning Language Models from User Interactions
Fast-weight Product Key Memory
Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
Merging Adapted Models via Data-Free Covariance Estimation
On the Importance of Trivial Baselines: Re-evaluating LoRA Adapter Transfer for Generative Tasks
Sparse structured matrices: Efficient adapter rank in fine-tuning Foundation models
Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio
Externalizing Plasticity: Zero-Update Continual Learning via Symbolic Memories
Semantic Grouping with Dual-Strategy Distributional Rehearsal for Continual Learning
SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
Audit Before You Merge: Provenance, Probing, and Continual LoRA Composition
Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents
REPO: Detoxifying LLMs via Representation Erasure-based Preference Optimization
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
Hard-First: Entropy-Guided Curriculum Distillation Balances Transfer and Preservation in Biomedical Vision-Language Models
Functional Task Networks: Cortex-Inspired Spatial Parameter Isolation for Continual Learning
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Mitigating Catastrophic Forgetting in Continual RL via Certified Alignment
DECAF: De-Clustering for Adaptive Representational Unlearning
On-Policy Adaptation Mitigates Hyperparameter-Sensitive Forgetting in Vision-Language Models
Test-Time Training for Visual Foresight Vision-Language-Action Models
Machine Studying: A System-Level Reframing of Continual Adaptation from Declarative Corpora
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
Rotation-Preserving Supervised Fine-Tuning
Characterizing Plastic Regions in Neural Networks
Continual Learning of Physical Systems via Derivative Distillation
MeMo: Memory as a Model
Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
Orthogonal Mixture-of-Expert Low-Rank Adapter for Continual Learning
AV-CTTA: Audio-Visual Continual Test-Time Adaptation without Forgetting
Route, Reuse, Repurpose: Continual Adaptation of LLMs with Bounded Adapter Pools
A loss curvature account of fine-tuning fragility
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
Organized Plasticity for Cost-Bounded Continual Adaptation
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
Calibrated Target-Aware Data Selection for Continual Mid-Training in Streams
Factor Imbalance and Plasticity Loss in Low-Rank Factorized Networks
Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation
RA-LoRA: Rank-Adaptive Low-Rank Adaptation via Subspace Interference Measurement for Continual Fine-Tuning of Foundation Models
Experience-Guided Behavior Adaptation for Large Language Models
Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation
Measurement Plasticity: Sensor-Level Adaptation for Vision–Language Models
Selective Memory Retention for Long-Horizon LLM Agents
Provable Forgetting Bounds Drive Capacity Savings: Spectral Thresholding in Continual LoRA
RepSelect: Robust LLM Unlearning via Representational Selectivity
Continual Causal Refinement: Learning from Sequential Perturbation Data
Beyond Classification: Continual Learning for Multimodal Retrieval