HERD (Harness-Evolving Recursive Distillation) is a hybrid continual learning framework that combines harness-based non‑parametric methods with parametric distillation. It refines reusable skills in a harness while storing high‑residual examples in bounded memory, and applies drift‑constrained distillation with dual anchors to reduce forgetting. On the 25‑stage TRACE+17 task stream, HERD matches the best parametric baseline in new‑task learning while achieving the lowest forgetting and strongest retention of general capabilities under fixed memory and compute budgets.
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv:2609.17026v1 Announce Type: new Abstract: Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a da...
arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.
arXiv:2404.07729v2 Announce Type: replace Abstract: Continual learning (CL) evaluates adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forg...
arXiv:2609.38833v1 Announce Type: new Abstract: Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting...
arXiv:2607. 01763v1 Announce Type: new Abstract: Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities.
MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.
arXiv:2601. 19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.
The paper introduces HaMo, a Harness-Model collaborative framework designed for long-horizon continual learning. HaMo combines fast non‑parametric experience accumulation—distilling trajectories into strategy‑level experience cards for immediate retrieval—with slow parametric adaptation, training the model to interpret, ground, and execute these strategies across changing contexts. A retrieval‑coverage‑based selection mechanism identifies compact, complementary trajectories for parameter updates, and experiments demonstrate that HaMo outperforms both harness‑only and model‑only approaches in within‑domain and cross‑domain settings, improving retention and adaptation.
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach.
The paper demonstrates that off‑policy merging, called grafting, outperforms on‑policy self‑distillation for continual learning. Grafting learns updates on an earlier donor checkpoint, scales the update, and optionally masks sensitive directions, thereby reducing interference with existing capabilities. Across various continual learning scenarios, grafting achieves better new‑task and old‑task performance without costly on‑policy sampling.
arXiv:2407. 13911v5 Announce Type: replace-cross Abstract: Prompt-based continual learning has shown strong performance in rehearsal-free class-incremental learning by adapting learnable prompts while freezing a pre-trained Vision Transformer (ViT) backbone.