The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory

• URL: http://arxiv.org/abs/2607.19390v2
• Date: Thu, 23 Jul 2026 12:47:31 GMT
• Title: The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory
• Abstract summary: The effect replicates, but it is not a memory improvement.<n>Training on this task is a long chance plateau followed by a sharp escape.<n>Much of the published gain needs no architecture at all.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Raven: High-Recall Sequence Modeling with Sparse Memory Routing [88.47618436676748]
  We introduce Raven, a linear-time sequence model that maintains a fixed set of memory slots and, at each step, decays and updates only a selected subset via learned, input-dependent routing.<n>Across recall-intensive benchmarks, Raven is competitive with or outperforms prior linear-time baselines, achieving strong long-context recall where both SWA and SSMs sharply degrade.
  arXiv  Detail & Related papers  (2026-07-28T07:04:32Z)
• Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps [4.422349568747053]
  We study the phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining.<n>We give a provable account of which case obtains robustness, and it turns on two properties together: the structure of the gradient noise and whether the structure of the gradient noise normalizes its update.
  arXiv  Detail & Related papers  (2026-07-14T05:21:38Z)
• Learning to Solve Generative ODEs Beyond the Linear Span [50.13853710831612]
  We propose SpanLift, a lightweight neural solver that augments scalar-coefficient updates with a spatial residual operator.<n>Across pixel-space diffusion, latent flow matching, and precipitation nowcasting, SpanLift achieves state-of-the-art few-step sampling.
  arXiv  Detail & Related papers  (2026-06-07T15:22:13Z)
• PURGE: Projected Unlearning via Retain-Guided Erasure [5.069332646113575]
  PURGE is a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU)<n> CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions.<n> PURGE consistently keeps accuracy above 96% while achieving MIA AUROC close to 0.5 (the ideal), outperforming gradient ascent, KL-uniform, and several published baselines on the privacy-utility frontier.
  arXiv  Detail & Related papers  (2026-06-02T15:53:01Z)
• Fast Unlearning at Scale via Margin Self-Correction [52.46927918952516]
  Language-model unlearning updates a trained model to behave as if it had not seen selected training examples.<n>MASC achieves a competitive forget-retain trade-off at a fraction of the computational cost of existing baselines.
  arXiv  Detail & Related papers  (2026-06-01T21:49:54Z)
• Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation [89.70897512515477]
  Action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response.<n>Maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging.<n>Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from textitLatent--RGB Cycling, and the training--inference gap induced by the textiterror-free hypothesis.<n>We present textbfRobust Dreamer, a memory-augmented framework built around how to
  arXiv  Detail & Related papers  (2026-05-29T05:21:33Z)
• AEL: Agent Evolving Learning for Open-Ended Environments [43.56685432981852]
  We introduce emphAgent Evolving Learning (ael), a two-timescale framework that addresses this obstacle.<n>ael achieves a Sharpe ratio of 2.13$pm$0.47, outperforming five published self-improving methods.<n>This demonstrates that the bottleneck in agent self-improvement is emphself-diagnosing how to use experience rather than adding architectural complexity.
  arXiv  Detail & Related papers  (2026-04-23T14:29:25Z)
• Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design [2.28438857884398]
  We study routing games in which travelers optimize over routes that are remembered or surfaced, rather than over a fixed action set.<n>The paper develops a tractable design theory for endogenous recall and then connects it back to an explicit finite-memory micro model.<n>For larger memories, we develop an explicit LRU-to-TTL-to-salience approximation pipeline and add contraction-based bounds that translate surrogate-map error into fixed-point and welfare error.
  arXiv  Detail & Related papers  (2026-04-13T17:08:47Z)
• Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning [71.96329385684395]
  We propose model extrapolation as an alternative to gradient ascent (GA)<n>Counterfactual as it might sound, a forget model can be obtained via extrapolation from the memorization model to the reference model.<n>Our model extrapolation is simple and efficient to implement, and it can also effectively converge throughout training to achieve improved unlearning performance.
  arXiv  Detail & Related papers  (2026-02-06T07:11:27Z)
• Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability [1.078600700827543]
  We build a simple model-agnostic witness of training memory based on emphback-flow of distinguishability.<n>We observe consistent positive back-flow with tight bootstrap confidence intervals, amplification under higher momentum, and more micro-steps.<n>We position this as a principled diagnostic and empirical evidence that practical SGD deviates from the Markov idealization.
  arXiv  Detail & Related papers  (2026-01-23T09:03:25Z)
• Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression [53.48692193399171]
  Gated KalmaNet (GKA) is a layer that reduces the gap by accounting for the full past when predicting the next token.<n>We solve an online ridge regression problem at test time, with constant memory and linear compute cost in the sequence length.<n>On long-context, GKA excels at real-world RAG and LongQA tasks up to 128k tokens, achieving more than $10$% relative improvement over other fading memory baselines.
  arXiv  Detail & Related papers  (2025-11-26T03:26:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.