Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows linearly during autoregressive inference. Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state, but often underperform on recall-intensive tasks since earlier associations usually get overwritten by subsequent updates, and only the most recent contextual information is retained. In this paper, we introduce Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension, while maintaining computational efficiency over long-sequences. MARCH periodically caches cumulative recurrent-state checkpoints as state anchors and associates each anchor with a compact, content-conditioned anchor key. This lets MARCH maintain a memory bank, which can grow as context length increases, providing a controllable trade-off between historical resolution and memory cost. At each token, MARCH produces an anchor query to attend all causally available state anchors, and the output is calculated as an attention-style aggregation over all historical anchors along the current state. We show that after standard pretraining, MARCH consistently outperforms multiple linear attention variants across commonsense reasoning, LongBench, and in-context retrieval. These results demonstrate that content-routed state caching substantially strengthens recurrent long-range memory while preserving its native computation path.
Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose \textbf{Ripple}, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuously summarize audio and video context. Cross-modal memory interaction is further introduced to enhance audio-visual synchronization. To learn this memory-augmented model effectively, we devise a three-stage training recipe: (1) adapting a bidirectional audio-video teacher to block-wise causal attention with simulated memory, (2) optimizing the memory construction and interaction pipeline through end-to-end distillation, and (3) applying online reinforcement post-training tailored for streaming audio-video generation. As a result, Ripple achieves ~28 FPS at 480P resolution, over faster than the teacher, while capable of coherent long-form generation. Extensive experiments on both short-video and long-video benchmarks demonstrate our superior performance over existing offline and online joint audio-video generation methods.
A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves noisy associative recall. The effect replicates, but it is not a memory improvement. Training on this task is a long chance plateau followed by a sharp escape, and the orthogonalized read acts by re-conditioning the learning problem during the plateau. Three properties establish this. It must be self-consistent: an exact recursive least-squares read (the Mesa layer) reproduces it, while straight-through halves, delta-rule writes, frozen random keys, and plain normalization all fail. It is uniform: across a learning-rate x hardness grid it multiplies the escape hazard roughly six-fold with no detectable hardness dependence, widening the workable learning-rate corridor that narrows for the baseline. And it is removable: applied to failed models at inference it rescues none, and annealed away on an escape-triggered schedule it leaves numerically stock mLSTMs at full accuracy. Much of the published gain needs no architecture at all: solved-rate at a fixed budget measures escape hazard, which follows a heat/noise law (learning-rate elasticity +3.0, gradient-noise elasticity -1.65) under which the original vocab-96 result is a large-batch noise condition rather than a capacity one. Decoding the memory state directly shows failed models carry roughly half their associations in linearly recoverable form: the plateau is a readout failure over half-written storage. Two conclusions travel beyond the intervention: recall benchmarks used for architecture selection partly measure trainability, and the system is a fully instrumented model organism of "emergence," in which a sharp behavioral threshold demonstrably arises from a censored metric over gradually accumulating structure.
Jiatong Li, Samuel Yeh, Sharon Lics.LG cs.AI cs.CL
Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window. Despite their scalability, these agents exhibit a well-documented reliability problem: end-to-end performance degrades systematically as context length grows. We diagnose this failure by decomposing performance into two factors--memory capture and memory retention--and quantitatively confirm that retention is the dominant bottleneck. Retention collapses because existing designs maintain memory as a monolithic text block, forcing every update to risk overwriting previously retained content. Motivated by this diagnosis, we propose Multi-Head Recurrent Memory (MHM), a general, training-free framework that partitions memory into independent heads governed by a stage-wise select-then-update strategy. At each step, exactly one head is selected for update while the remaining heads are structurally shielded from overwriting, shifting the burden of retention from model behavior to architectural design. As a lightweight instantiation, we introduce Least-Recently-Updated MHM (MHM-LRU), which guarantees uniform head utilization with zero additional token overhead. Extensive experiments on long-context benchmarks show that MHM-LRU substantially improves both retention and end-to-end accuracy across the 100K--1M token range, where baselines degrade sharply. On RULER-HQA at 896K tokens, MHM-LRU improves the memory retention rate from less than 30% to 73.96%. These gains generalize across model families, scales, and task types, positioning architectural optimization as a practical and cost-efficient path toward reliable long-context recurrent memory.
Length extrapolation in language models involves competing objectives: retrieval fidelity, long-document likelihood, short-context quality, and inference cost. We present ATMA, a 378M-parameter hybrid recipe that combines Polar Attention with gated-delta recurrent memory, and study these objectives as a Pareto problem rather than claiming general architectural dominance. Polar Attention separates a normalized direction channel from a bounded participation-ratio magnitude channel. We select the recipe with a complete 120-cell, 1B-token factorial sweep, then train matched NoPE, RoPE, and Polar variants for 9.816B tokens at length 2K and evaluate them through 256K. Across the factorial, memory improves Polar's 64K retrieval score in all 20 matched cells (mean +47.8 points), whereas its effect on NoPE is small and inconsistent. At 256K, Polar retains 34.4% teacher-forced target-token accuracy and 9.0% exact five-token accuracy; exact retrieval is 18.0% on synthetic contexts but 0.0% on FinePDFs contexts. Polar also limits mean fixed-target bits-per-byte degradation to 1.26 times, at a 1.9-point mean cost on eight short-context tasks. Raven baselines lead BABILong and have length-independent decode state, illustrating a different point on the frontier. Finally, a post-hoc checkpoint audit shows that nearly identical 2K validation curves can conceal a 6.70-nat difference at 256K. Because those runs were neither seed-paired nor randomized across devices, we interpret this as checkpoint variability associated with an infrastructure transition, not a causal hardware effect. Code: https://github.com/kreasof-ai/atma
Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on information no longer visible. Existing memory-augmented VLAs simultaneously introduce recurrence, retrieval, compression modules, auxiliary objectives, hierarchical memory, or task-specific architectural changes, so the contribution of recurrence itself remains entangled with surrounding machinery. We present a controlled isolation study of recurrence in a strong pretrained VLA backbone. Our formulation augments the transformer with a small set of learnable memory tokens carried across timesteps and updated through self-attention, trained end to end with truncated backpropagation through time, with no auxiliary losses and no architectural changes. We instantiate this as $μ$VLA, a family of OpenVLA-OFT variants parameterized by memory width m, TBPTT length K, and the memory update rule (cross-step gradients or a detached EMA), so that recurrence is the only varying factor. On MIKASA-Robo, $μ$VLA improves average success rate on five training tasks from 0.42 to 0.84 at the strongest setting and reaches 0.23 on held-out tasks with the same memory structure versus 0.07 for the memoryless baseline. On tasks requiring different memory structure, performance remains near baseline. On LIBERO, the strongest recurrent variant achieves 96.2% average success, indicating no regression under full observability. We interpret these results as a calibration of the capability envelope of minimal in-backbone recurrence, identifying the regime in which it is sufficient and the regime where additional memory structure is required. Demos and videos can be found in https://avanturist322.github.io/mu-vla/.