arXiv:2607. 19749v1 Announce Type: cross Abstract: Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience.
ReDraft is a reference‑driven revision method for continual post‑training of large multimodal language models. It uses the model’s own incorrect outputs as references, revises them, verifies the revisions, and fine‑tunes on the accepted ones, thereby combining explicit supervision with policy proximity. On tasks such as Counting, Clock Reading, and Jigsaw, ReDraft outperforms standard supervised fine‑tuning and on‑policy methods, achieving higher target‑task gains while dramatically reducing forgetting.
arXiv:2604. 15414v2 Announce Type: replace-cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks.
arXiv:2602. 03846v2 Announce Type: replace-cross Abstract: We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable.
arXiv:2608.20965v1 Announce Type: new Abstract: We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and rel...
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.
arXiv:2606. 30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces.
arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.
The paper demonstrates that adding stochastic noise to a consolidation rule can improve a neural network’s retention of earlier tasks up to an optimal level, after which performance degrades, forming an inverted‑U relationship. Through simulations on related‑task continual‑learning benchmarks, the authors isolate the conditions that produce this optimum, showing it requires coherent restoration toward consolidated weights and is linked to the noise variance. The study further maps the scope of the effect, noting it depends on shared task structure and diminishes with more tasks, while a single‑seed hardware demonstration is referenced elsewhere.
arXiv:2510. 07648v3 Announce Type: replace Abstract: Feature-space objectives are often added to replay-based continual learning systems with the expectation that better geometric separation will improve retention.
arXiv:2607. 21000v1 Announce Type: new Abstract: Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones.