cs.LGNov 3, 2026

Attending to Memory Writes Reduces Seed Variability in Recurrent Length Generalization

Authors: Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

Organizations: College of Pharmacy, Chungnam National University, Daejeon, Republic of Korea · Department of Computer Science & Engineering, Chungnam National University, Daejeon, Republic of Korea

Abstract

Recurrent memory requires learning useful updates, but attention added to assist learning can also compromise length generalization. We study bounded delta attention: causal attention over uncorrected update proposals whose bounded correction enters the recurrent update. Its implementation in TraceRelay combines additive phase recurrence with attention computed before a parallel scan. On prefix-supervised modulo-5, trained at lengths 1--40, three findings characterize its behavior at length 80. First, upper delta attention attains 70.81±8.2670.81\pm8.26% accuracy across seven seeds, versus 69.21±22.4269.21\pm22.42% for the local-attention recurrent baseline (mean ±\pm sample SD): a 63.2% reduction in SD with a similar mean. Upper state attention also reduces variation, reaching 74.75±6.2474.75\pm6.24%, so this benefit is not unique to update-level attention. Disabling the upper delta correction retains 70.62±8.6070.62\pm8.60%. Second, blocking gradients at the delta-attention inputs changes accuracy to 65.25±12.4065.25\pm12.40% in the matched seven-seed comparison, increasing SD by 50.2%. It also delays a 99% validation threshold on average among the same six seeds that reach it; the 95% threshold is reached earlier on average with input-gradient blocking across all seven seeds. Third, lower delta attention exhibits substantially less extrapolation degradation than lower state attention: 62.60% versus 19.40%, against a 71.06% baseline. Removing its correction reduces accuracy to 22.56%; its advantage over lower state attention also persists under input-gradient blocking. These observations motivate bounded update-level attention as a recurrent learning scaffold, combining reduced seed variation with less severe degradation in a placement where state attention fails.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 8, 2026

TraceRelay: Attention-Aligned Recurrence over Rolling Traces

We present TraceRelay, an attention-aligned recurrent architecture that distributes persistent representations over a rolling sequence of low-dimensional traces. Local right looking attention forms increments from lower-layer representations; delivery is delayed until all attended inputs are in the causal past. A fixed additive phase recurrence accumulates the delayed increments, and left-looking attention reads the resulting residual augmented stream. A stride-wise prefix sum supports parallel prefill and bounded-buffer continuation. We study 36 small-model runs on Equal Repeats, bounded Dyck closing-type prediction, and causal Most-Freq generation, using three seeds per setting. At trained length 256, Equal Repeats models with recurrent phase inheritance reach 98.81-99.69% accuracy versus 50.73-51.63% for separately trained variants without inheritance, despite the latter receiving more updates. Accuracy drops sharply at lengths beyond the training range. At the longest evaluated lengths, models with more dimensions in the middle layer's recurrent traces perform better on Dyck (76.34% versus 55.49% close accuracy at length 4096), whereas models with fewer trace dimensions perform better on five-symbol Most-Freq (70.74% versus 55.60% exact generation at length 1024). These contrasting cases motivate further study of how the size of recurrent representations should be chosen for different tasks, without establishing a general rule across tasks or model configurations.
Jun 25, 2026

Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a different address cannot be actively removed before new content is written elsewhere. We propose Erase-then-Delta Attention (EDA), a memory update rule that decouples where to erase from where to write. The key insight is that recurrent memory models should not only correct the current write, but also selectively suppress outdated memory at an independently chosen address. Concretely, our method first applies a targeted erase step along a learned erase direction, and then performs the standard delta-style corrective write along the current write direction. This preserves the corrective behavior of delta-rule updates while expanding their memory-management capacity. Language-model pretraining experiments across dense 2.5B and MoE 25B-A2.8B model families show that EDA performs best in both settings. The gain persists after 80B-token long-context midtraining of the MoE models, where EDA also performs best in long-context evaluations from 4k to 128k contexts. A compact update analysis and memory-state probes suggest why: EDA keeps the delta-rule corrective write intact while allocating an additional cleanup path most strongly when passive decay is weak. These results suggest that recurrent memory models should decide not only what to write, but also what stale information to erase and where.
Aug 27, 2026

Fast Weight Attention for Continual Learning

Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning rule. We study this rule under read-after-write autoregressive semantics. For the prefix-prediction objective considered here, the local fast-memory example revealed at step tt is the prefix-aligned pair (xt,yt)=(φ(kt−1),vt)(\mathbf{x}_t,\mathbf{y}_t)=(φ(\mathbf{k}_{t-1}),\mathbf{v}_t). The common same-step association (φ(kt),vt)(φ(\mathbf{k}_t),\mathbf{v}_t) remains causal, but optimizes a different internal objective. We derive normalized first-order updates for squared-error regression and negative inner-product objectives. The regression family comprises Falcon-1 (a scalar NLMS update), Falcon-2 (its per-column extension), and Falcon-3 (a sliding-window mini-batch update); Falcon-1A/Falcon-2A/Falcon-3A are the corresponding inner-product variants. We provide recurrent, masked-parallel, and chunk-parallel forms, together with numerically stable positive-decay renormalization. Representative variants remain competitive in language modeling and improve length extrapolation on variable-digit addition. This framework separates temporal alignment, plasticity, forgetting, and bounded rehearsal in recurrent sequence models.