NeurIPS 2026 Papers

Replay is a standard strategy for mitigating catastrophic forgetting in continual learning, where a bounded memory buffer stores exemplars from previously seen classes. Existing replay methods have largely focused on instance-level decisions, such as which samples to store, replay, or replace, while the class-wise allocation of memory slots is often treated as a uniform heuristic. Here, we study class-wise memory allocation as a complementary design axis and propose VAMA, a value-aware memory allocation framework. VAMA keeps cross-task budgets balanced, estimates task-local class values from Shapley-inspired sample utility scores, and converts them into class-wise quotas through a regularized allocation rule that conservatively deviates from class-balanced replay. This design changes only the class-wise budgeting rule and leaves within-class exemplar selection unchanged, making VAMA easy to integrate into replay pipelines. Experiments on CIFAR-100 and ImageNet-100 show that VAMA consistently improves ER, iCaRL, and FOSTER across different memory budgets and task protocols. Further analyses show that the improvements are not due to non-uniform allocation alone, and that allocation-relevant class-value rankings stabilize early in training, enabling efficient value-aware allocation. These results suggest that class-wise memory allocation is a consequential design choice in replay-based continual learning.

Backpropagation imposes fundamental constraints on training neural networks. It requires the retention of all forward activations until the corresponding backward pass completes, thereby preventing pipelined execution across layers. This work introduces Backpropagation-Free Local Antithetic Node Perturbation (BLANP), a fully local training framework that eliminates gradient propagation across layer boundaries while requiring no negative samples. Each layer updates its parameters from locally available signals through a zeroth-order antithetic perturbation estimator. To stabilize learning, the estimator is evaluated against a frozen exponential moving average critic, decoupling backbone updates from the concurrently evolving local classifiers. The antithetic perturbation formulation cancels even-order bias terms in the gradient estimate, yielding a first-order accurate update from two forward passes alone. A companion variant, BLANP-Exact, replaces the perturbation estimator with exact yet local gradients under a strict stop-gradient constraint, preserving a memory footprint that does not grow with network depth while recovering gradient fidelity. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 across MLP and convolutional architectures show that BLANP matches backpropagation on simple benchmarks. On the more challenging CIFAR-10, BLANP-Exact surpasses the best prior local learning method by 2.40% with a simpler architecture, and trails an identical backpropagation baseline by only 3.90%. The code is available at https://github.com/anonymous/BLANP.

Sequence models in machine learning compress long input histories into finite-dimensional states, from recurrent networks and reservoir computing to recent state space models for long-context data. This raises a basic expressivity question: how simple can the recurrent memory be before it can no longer approximate stable causal sequence-to-sequence maps? We answer this question for fading-memory operators, where the distant past has uniformly diminishing influence. We show that every continuous causal time-equivariant fading-memory operator on a compact input set can be uniformly approximated by a state space model whose recurrence is a fixed diagonal linear contraction. The dynamics are time-invariant, input-independent, and contain no nonlinear hidden-state update or delay-line structure. The construction uses a bank of short exponential traces; although such traces do not exactly store a recent input window, a singular Vandermonde extraction approximately reconstructs the window while the remaining tail becomes negligible as delta decreases. We also prove that exact delay recovery is impossible for any fixed finite trace bank, showing that the accuracy-dependent extraction is essential. Technically, the result separates recurrent expressivity from exact memory storage, while exposing a conditioning cost in the readout. More broadly, it clarifies why highly stable, structurally simple SSM cores can still be universal approximators for stable sequence behavior.

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge---a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class memory actions alongside task actions, letting the model itself decide how to manage its memory. This memory skill improves along two axes: the structure that supports it (prompts, file schemas, action vocabulary), and the proficiency of the model exercising it. Both axes resist manual optimization: episodes in long-horizon tasks run for thousands of steps, and a single memory mistake can hide long before it surfaces, making human review of full trajectories impractical. We introduce AUTOMEM, a framework that automates both axes. In the first loop, a strong LLM reviews complete agent trajectories and iteratively revises the memory structure that shapes how the agent interacts with its memory files. In the second loop, the agent's own good memory decisions are identified from many episodes and used as training signal to sharpen the model's memory proficiency directly. Across three procedurally generated long-horizon games (Crafter, MiniHack, and NetHack), optimizing memory alone---without modifying the model's task-action behavior---improved the base agent's performance 2x--4x, bringing a 32B open-weight model competitive with frontier systems such as Claude Opus 4.5 and Gemini 3.1 Pro. Our results show that memory management is an independently learnable skill, and a high-leverage objective yielding large gains on long-horizon tasks.

Temporal sequences in working memory are hierarchically organized to support flexible behavior. Recent neural recordings suggest that this organization relies on a 1D-to-2D neural geometrical folding in working memory, whereby ordinal positions are re-encoded within an orthogonal scaffold, with two dimensions indexing global (chunk-level rank) and local ranks (within-chunk position), respectively. This findings implicate an important structural principle for memory, yet the computational mechanisms underlying this geometry remain unclear. Here, we study this question using a recurrent neural network with fast Hebbian plasticity (Hebb-RNN). When meta-trained on rank recalling tasks, the Hebb-RNN generalizes to novel item–rank bindings and hierarchical sequences, outperforming control models. Mechanistic analysis reveals that the network develops an orthogonal ordinal geometry consistent with empirical findings. This geometry transforms temporal inputs into abstract ordinal ranks that provide a memory scaffold, while Hebbian plasticity supports rapid conjunctive binding of item content to this structure. Furthermore, the pre-learned geometric scaffold significantly accelerates learning in novel tasks, supporting efficient transfer. By incorporating a predictive module, our model extends to real-world encodings and acquires hierarchical geometry without explicit chunking signals. Together, our results provide a biologically plausible framework for hierarchical sequence representation, offering new insights into structured memory organization for both neuroscience and machine learning.