Memory-Augmented Neural Networks

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 63

Jun 23, 2026cs.CV

SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking

We revisit the memory update mechanism in SAM2-based visual object tracking and identify confidence-only mask selection as the dominant cause of drift under occlusion, rapid motion, and distractors. We introduce SENTRY, a training-free, plug-and-play, refine-before-write module that validates each memory update for short-horizon temporal consistency before committing it. SENTRY aggregates diverse segmentation hypotheses per frame, backtracks them into short tracklets, and uses neighbor-aware cycle-consistent matching against recent trajectories to favor temporally and geometrically consistent masks. It leaves the base architecture untouched, replacing confidence-driven writes with consistency-validated ones. For fair evaluation, we re-evaluate major open-source SAM2-based trackers across all available scales and datasets, filling gaps in prior reports. Integrated into five strong baselines, SENTRY delivers consistent gains across nine benchmarks, achieving new zero-shot SOTA on LaSOT, LaSOT_ext, GOT-10k, VOT20, VOT22, and DiDi. Despite these checks, the SAM2-L version runs at 32.8 FPS on an A100, and across compatible hosts adds only about 0.4--0.6 GB VRAM. Our results provide the first unified all-scale evaluation of SAM2-based trackers and show that enforcing temporal validity at write time stabilizes memory-augmented tracking without retraining. Project page: https://hamadya.github.io/SENTRY/page/

Mohamad Alansari, Yonathan Michael, Hasan AlMarzouqi +3

Khalifa University, Abu Dhabi, UAE · University of Western Australia, Australia

Memory-Augmented Neural Networks Visual Object Tracking Segment Anything Models

Jun 23, 2026cs.LG

Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping

Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}. However, adapting these frozen memory systems to new tasks presents a fundamental ``Plasticity-Stability'' dilemma. Current methods either risk catastrophic interference by modifying synaptic weights directly (e.g., LoRA) \citep{hu2021lora} or degrade associative capacity by clogging the retrieval buffer with static prompt tokens (e.g., VPT) \citep{jia2022vpt}. In this work, we propose \textbf{H-Res} (Hierarchical Residual Steering), a mechanism that modulates the effective energy landscape of the Transformer without altering its global equilibrium or expanding its sequence length. By formulating adaptation as a control problem on the activation manifold \citep{chen2018neuralode}, H-Res learns a state-dependent vector field that steers token trajectories into task-specific basins of attraction. We formally prove that H-Res preserves the attention entropy of the foundation model and facilitates Neural Collapse \citep{papyan2020prevalence}. Empirically, Manifold Steering outperforms global weight modification by 26% on associative retrieval tasks and eliminates the computational overhead of prompt-based methods, scaling effectively to structured domains \citep{zha2023vtab}.

Kanishk Awadhiya

Independent Researcher

Memory-Augmented Neural Networks Transformer Attention Activation Steering Associative Memory Parameter-Efficient Fine-Tuning

Jun 17, 2026cs.AI

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory

We study factual edit propagation in a controlled synthetic knowledge-graph QA setting using a 2x2 grid that crosses loop recurrence with shared-memory access: a dense transformer (Dense), a looped transformer (Loop), a dense backbone with shared memory (Dense+Mem), and a looped backbone with shared memory (loop-memory coupling, LMC). The two factors dissociate. For learning, both routes to repeated shared access -- looped recomputation and repeated memory rereading -- cross the out-of-distribution (OOD) grokking barrier that Dense fails, so repeated shared access is the behavioral regularity, not a specific architecture. For editing, the substrates split along a different axis: applying a single localized factual edit (conditioned on direct success) and measuring 2-hop propagation on a shared pre-edit-correct set, the edit propagates strongly in both memory-bearing cells (LMC 0.78-0.92, Dense+Mem 0.71-0.96) and only weakly in the memory-free ones (Loop 0.04-0.30, Dense 0.00-0.03). The split is along the memory axis, not the loop axis: every memory-bearing seed exceeds every memory-free seed, with no detectable difference between the two memory cells. Crucially Dense+Mem has no recurrence, so the propagating ingredient is an addressable site that an edit can write to and later computation rereads, not loop recomputation; Loop is at best a partial intermediate. The affordance survives coarsening the store (N=128 to N=13): propagation attenuates but the memory/no-memory split persists, so fine granularity buys precision rather than the affordance itself. These results dissociate learning competence from editing affordance -- repeated shared access suffices to grok, but edit propagation depends on whether the substrate exposes an addressable memory that the forward computation can write to and later reread, an affordance that loop recurrence provides only partially.

Yanan Niu

Kuaishou Technology

Memory-Augmented Neural Networks Knowledge Editing Recurrent Transformers Model Editing Grokking

Jun 15, 2026cs.CV

When the Past Matters: FlashBack Memory for Precipitation Nowcasting

Accurate precipitation nowcasting is crucial for disaster mitigation and socio-economic planning, yet existing methods often struggle with false alarms, missed events, and long range dependency modeling at high spatiotemporal resolution. To address these challenges, we propose FlashBack Memory (FB), a module that dynamically retrieves key historical states and integrates them via an adaptive fusion gate, enhancing the spatiotemporal representation capability of recurrent-based models. We incorporate FB into PredRNN, PredRNNpp, MIM, MotionRNN, and PredRNN-V2, and evaluate on CIKM2017, Shanghai2020, and SEVIR datasets. Experimental results demonstrate that FB significantly improves MSE, MAE, SSIM, and CSI metrics, particularly for high-intensity rainfall and long-sequence predictions, while reducing false alarms and missed events and enhancing temporal consistency and spatial localization. The proposed method provides a general and efficient memory enhancement mechanism, improving the overall performance of recurrent-based precipitation nowcasting models.

Yuhao Du, Boxiao Huang, Chengrong Wu +1

College of Atmospheric Sciences, Lanzhou University, Lanzhou 730000, China · Fuqua School of Business, Duke University, North Carolina 27705, USA · Department of Computer Science, University of Manchester, Manchester M139PL, UK

Memory-Augmented Neural Networks Precipitation Forecasting Recurrent Neural Networks Spatiotemporal Forecasting Precipitation Nowcasting

Jun 14, 2026cs.LG

The Reservoir Attention Network: Cross-Pass State in Pretrained Transformers via Content-Addressable Reservoir Injection

A feasibility and dynamics study of the Reservoir Attention Network (RAN), an architecture that injects a fixed, randomly-initialized reservoir into the mid-layer attention of a pretrained transformer to carry state across forward passes. Experiments span GPT-2 (124M, 355M) to Qwen2.5 (0.5B, 1.5B) on a single consumer GPU. The tasks are minimal probes chosen to isolate individual mechanisms; the broader always-alive agent vision is treated throughout as compute-limited future work, not a claim of this paper. The reservoir is left untrained (fixed random) by design: this isolates whether untrained recurrent dynamics alone suffice to carry usable cross-pass state, leaving trained recurrence as a complementary, more expensive direction.

Emma Leonhart

Memory-Augmented Neural Networks Persistent Memory for Language Models LLM Memory Reservoir Computing Recurrent Transformers

Jun 11, 2026cs.LG

How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators

Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances, memory-augmented neural operators explicitly incorporate past states and have achieved remarkable performance under low-resolution observation settings. However, existing approaches apply a fixed memory weight regardless of observation conditions, such as resolution or physical parameters, limiting their adaptability. Our preliminary experiments reveal that optimal memory weight varies with resolution and viscosity, implying that a fixed memory weight cannot simultaneously optimize performance across diverse settings. We propose AMGFNO, which dynamically modulates memory weight through a learnable gate. On the Kuramoto-Sivashinsky and Burgers' equations, AMGFNO achieves 55-79% nRMSE reduction over at low resolution, with the learned gate value automatically decreasing from

\bar{g} \approx 0.7

to near-zero as resolution increases.

Jihyeon Hur, Yongseok Kwon, Min-Gi Jo +2

1KAIST, Republic of Korea.

Memory-Augmented Neural Networks Fourier Neural Operator PDE Operator Learning Neural Operators

Jun 10, 2026cs.LG

MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry

De novo peptide sequencing from tandem mass spectrometry is pivotal in proteomics, enabling identification of novel peptides without reference databases. While recent Transformer-based encoder-decoder models have achieved remarkable performance, we uncover a critical pathology in their inference dynamics. Through comprehensive feature scaling experiments, we demonstrate that existing auto-regressive peptide decoders tend to over-rely on generated-sequence priors while progressively under-utilizing fine-grained physical evidence from the input mass spectrum. This phenomenon leads to suboptimal results, where generated peptide sequences are biologically plausible yet not faithful to the input spectrum. To rectify this, we propose MemNovo, a training-free and plug-and-play mechanism that re-balances peptide and spectral contributions at inference time. MemNovo alleviates the information bottleneck by establishing a persistent spectral memory bank and injecting retrieved features directly into the final decoding stage via an ultra-conservative residual connection. Theoretical analysis confirms that this mechanism restores the mutual information between the decoder state and the raw spectrum. Extensive experiments on the Nine Species benchmark with two representative baselines, Casanovo and InstaNovo, demonstrate that MemNovo consistently improves both amino acid precision and peptide precision, achieving up to 39.1% relative improvement in peptide precision for Casanovo and up to 3.9% for InstaNovo, with negligible computational overhead.

Dongxin Lyu, Jingbo Zhou, Hongxin Xiang +2

Westlake University Hangzhou, Zhejiang, China · Hunan University Changsha, Hunan, China · Shanghai Artificial Intelligence Laboratory Shanghai, China +1

Memory-Augmented Neural Networks Transformer Inference Mass Spectrometry Autoregressive Decoding

Jun 4, 2026cs.AI

AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks

Accurate vessel trajectory prediction is essential for safe and efficient maritime operations, enabling collision avoidance and supporting route optimization. Although memory-augmented neural networks have recently shown strong performance in pedestrian and road-vehicle trajectory prediction by selectively retrieving relevant information from an external memory, their potential for vessel trajectory prediction remains underexplored. This paper presents an empirical investigation of memory-based trajectory prediction using Automatic Identification System (AIS) data. Experiments on data from the Gulf of Mexico and the New York Bight demonstrate consistent and substantial performance gains over a range of deep learning baselines that do not incorporate an external memory.

Wonmo Koo, Sanha Chang, Heeyoung Kim

Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea.

Memory-Augmented Neural Networks Vessel Trajectory Prediction Trajectory Prediction

Jun 3, 2026cs.LG

SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks

Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be dominated by repetitive behavior patterns. We identify this phenomenon as semantic state sink, where recurring semantics over-occupy the recurrent state and bias subsequent readouts. To mitigate semantic state sink, we propose SinkRec, a hybrid memory-transition looped architecture that decouples collaborative behavioral pattern storage from dynamic transition modeling. SinkRec externalizes recurring local patterns into a learnable conditional memory through residual vector quantization, reinjects the retrieved codes, and exposes memory key-value pairs to the attention block. It further introduces Temporal-Aware State-Relation Differential Gated DeltaNet (TDGD), which uses memory to purify recurrent writing and reading by suppressing memory-covered updates and removing memory-aligned readout responses. This design turns recurring semantics from state-competing signals into memory-retrievable patterns, allowing the recurrent state to focus on dynamic transitions and alleviating semantic state sink with linear-time efficiency. Experiments on public and industrial datasets demonstrate the effectiveness and efficiency of SinkRec.

Zhuang Zhuang, Zhipeng Wei, Ji Dai +4

Kuaishou Technology, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China · Independent Researcher

Memory-Augmented Neural Networks Sequential Recommendation Linear Attention Gated Delta Networks

Jun 3, 2026cs.LG

RowNet: A Memory Transformer for Tabular Regression

Real estate valuation is a structured regression problem in which prices are governed by heterogeneous feature types, sparse regional effects, nonlinear interactions, and the practical logic of comparable properties. Standard multilayer perceptrons treat each row as an isolated vector and must learn locality, scale sensitivity, and categorical matching from supervision alone. Gradient-boosted decision trees provide strong tabular baselines, but their feature-centric splitting mechanism does not explicitly model the retrieval of similar historical observations. This paper presents RowNet, a retrieval-based neural architecture for real estate price-per-square-meter prediction. RowNet represents a query property through pairwise similarity features against a memory bank of labeled properties. A first retrieval layer estimates a coarse target from feature-only similarities. A second layer augments the memory comparison with target-consistency features and uses multiple learned attention heads to retrieve complementary comparable sets. A final mixture-of-experts module combines learned gating, residual correction, entropy regularization, and head-diversity regularization to produce the prediction.

Askat Rakhymbekov, Gulshat Muhametjanova

Department of Applied Mathematics and Informatics Kyrgyz-Turkish Manas University Bishkek, Kyrgyzstan · Department of Applied Mathematics and Informatics2026 Kyrgyz-Turkish Manas University Bishkek, KyrgyzstanJun

Memory-Augmented Neural Networks Tabular Regression

May 30, 2026cs.AI

SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition

Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive sequentially and must be processed in a single pass without simultaneously revisiting past observations. Standard architectures, including recurrent neural networks and transformers, are constrained by either truncated backpropagation through time horizon or explicit input window length for long range credit assignment. To address these limitations, we propose SHARP (Sleep-based Hierarchical Accelerated Replay), a framework that decomposes temporal learning into two complementary components: a memory module that accumulates a structured history of past inputs, and a pattern-recognition module that operates over this memory. This separation enables resource- and compute-efficient adaptation to non-stationary dynamics by eliminating the need for backpropagation through time across many steps for long-range credit assignment. Inspired by the accelerated replay observed in rodents during slow-wave sleep, SHARP incorporates offline (sleep) phases in which temporally structured memory traces are replayed in an accelerated form and integrated into higher-level memory representations, improving long-range context retention. Through controlled simulations and ablation studies, we characterize the key properties of the proposed framework. In benchmark datasets such as text8 and PG-19, we demonstrate that SHARP improves over recurrent baselines by retaining next-token predictive performance on previously seen data while continuing to learn from the current stream and generalizing to future unseen data. These gains are enabled by its hierarchical structure, which yields an exponentially increasing effective temporal context with only linear-time computational cost.

Jayanta Dey, Shikhar Srivastava, Itamar Lerner +2

University of Texas at San Antonio, USA · University of Rochester, USA

Memory-Augmented Neural Networks Continual Learning Long-Context Modeling Replay-Based Continual Learning Language Modeling Online Continual Learning+1

May 26, 2026cs.CV

Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial state, making long-horizon video understanding and occlusion-sensitive reasoning difficult. We propose Tensor Memory, a lightweight module that augments Transformer blocks with a fixed-size recurrent 3D memory tensor: tokens write into a voxel grid via a differentiable soft write that deposits content as a Gaussian-weighted volume around a predicted continuous 3D location, the memory is updated with an efficient local interaction operator and gated recurrent dynamics, and tokens read back context via continuous sampling with gated residual fusion. Because the memory tensor has a constant size, Tensor Memory decouples state capacity from input length while preserving a spatial inductive bias. We evaluate the module on standard language, image, and video benchmarks and on a controlled toy diagnostic suite designed to isolate when persistent state is beneficial; it integrates with standard Transformer training pipelines and can be attached to or removed from existing blocks without other architectural changes.

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2

Massachusetts Institute of Technology, Cambridge, MA, USA · University of Toronto, Toronto, Canada · IBM Research, Cambridge, MA, USA

Memory-Augmented Neural Networks Memory-Augmented Language Models Recurrent Transformers Long-Context Modeling Temporal Video Understanding

May 21, 2026cs.CL

What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA

Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Existing work trains exclusively on a single benchmark, leaving open how the composition of training data shapes the skills a memory agent acquires. We present a controlled empirical study that holds architecture, RL algorithm, and all hyperparameters fixed and varies only the training curriculum across three conditions: in-domain (LoCoMo), mixed-benchmark (LoCoMo + LongMemEval), and out-of-domain (LongMemEval only). Across two benchmarks and ten question types, curriculum composition acts as a fine-grained lever on specialization rather than a uniform scaling factor on performance. The mixed curriculum yields the strongest overall F1 on both evaluation sets. Training on a narrow out-of-domain set transfers a targeted skill - temporal reasoning - despite weak aggregate performance. Per-type differences substantially exceed aggregate differences, indicating that single-number benchmark comparisons systematically underreport curriculum effects. We further report two practical lessons from adapting GRPO to a single-GPU regime: cross-benchmark mixing requires filtering format-specific noise from memory banks to preserve training signal, and binary exact-match reward produces no learning signal at the small group sizes (G = 4) required on one GPU, motivating continuous reward functions in this regime.

Xinjie He, Zhiyuan Lin, Su Liu +4

Columbia University · Independent Researcher · Johns Hopkins University +1

Memory-Augmented Neural Networks Curriculum RL RL for LLM Agents Memory-Augmented Language Model Agents

May 21, 2026cs.LG

Tensor Cache: Eviction-conditioned Associative Memory for Transformers

Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the window becomes inaccessible. We introduce \emph{Tensor Cache}, a two-level cache that pairs sliding-window softmax attention as a first-level cache (L1) with a fixed-size outer-product fast-weight memory as a second-level cache (L2) fed by KV pairs evicted from the window. Recent tokens remain in exact local attention; evicted pairs are compressed into a per-layer matrix

A

and read by future queries through a single matrix multiplication, exploiting the linear-attention identity

q_t(k_i \otimes v_i)=\langle q_t,k_i\rangle v_i

. A learned scalar gate fuses the L1 and L2 outputs, and per-head decay and write-rate parameters are trained end-to-end. The outer-product memory and the read identity are well-known; our contribution is their use as an L2 cache fed exclusively by sliding-window evictions, plus identifying that the common chunked-mean training shortcut

A\!\leftarrow\!λA\!+\!η(\bar k\!\otimes\!\bar v)

silently introduces

C^2{-}C

spurious cross-token outer products per chunk, and closing the gap with a parallel weighted-sum scan equivalent to per-token writes within float32 epsilon. Across systems scaling, controlled associative recall, long-context language modeling, and memory-capacity diagnostics, Tensor Cache improves the memory--quality frontier over bounded-state baselines.

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2

Massachusetts Institute of Technology, Cambridge, MA, USA · University of Toronto, Toronto, Canada · IBM Research, Cambridge, MA, USA

Memory-Augmented Neural Networks Self-Attention KV Caching KV-Cache Eviction KV-Cache Management

May 18, 2026cs.LG

KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture

Time Series Foundation Models (TSFMs) have demonstrated notable success in general-purpose forecasting tasks; however, their adaptation to specialized classification problems remains constrained by the computational bottleneck of standard attention and the systematic omission of classical statistical knowledge. This technical report introduces KairosHope, a next-generation TSFM designed to reconcile massive generalization with analytical precision in classification tasks. The core of the proposal is the HOPE block, an architecture that replaces quadratic attention with a dual-memory system: Titans modules for dynamic short-term retention and a Continuum Memory System (CMS) for the abstraction of long-term historical context. To enrich the inductive bias, a Hybrid Decision Head is introduced, which fuses deep latent representations with deterministic statistical features extracted via tsfeatures package. KairosHope undergoes self-supervised pre-training on the massive Monash archive, combining Masked Time Series Modeling (MTSM) and contrastive learning (InfoNCE). Its subsequent adaptation to the UCR benchmark datasets is conducted through a rigorous Linear Probing and Full Fine-Tuning (LP-FT) protocol to prevent catastrophic forgetting. Empirical results demonstrate superior performance in domains characterized by strict temporal causality such as HAR or Sensor data. Consequently, KairosHope establishes a robust and efficient framework for the adaptation of foundation models to time series analysis.

Luis Balderas, José Alberto Rodríguez, Miguel Lastra +2

Department of Computer Science and Artificial Intelligence · DiCITS, iMUDS, DaSCI · Advanced Medical Imaging Group, Instituto de Investigación Biosanitaria de Granada (ibs.Granada) +3

Memory-Augmented Neural Networks Time Series Classification Self-Supervised Time Series Representation Learning Time-Series Foundation Models

May 15, 2026cs.CV

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to key-value caching, which limits its scalability to long video horizons. Existing remedies (e.g., sparse attention and KV-cache compression) reduce per-step cost but still rely on a linearly growing cache or irreversibly discard past context, and thus fail to address linear memory growth and streaming context management. To address this scalability bottleneck, we propose ARL2 (Attend Locally, Remember Linearly), a hybrid attention module that replaces quadratic cross-frame attention with a fixed-size recurrent state. We decompose self-attention into two branches: an intra-frame softmax branch for spatial detail and local dependencies, and an inter-frame gated recurrent linear branch that maintains a fixed-size state for streaming context. Our key insight is that softmax attention captures fine-grained local interactions, while a recurrent state provides controllable long-range memory. This design achieves linear-time scaling with constant memory while improving temporal consistency over the full-softmax model. To prevent noisy intermediate states from corrupting memory, we update the recurrent state only after the denoised pass. To avoid within-frame information asymmetry, all tokens share the same pre-update state rather than sequential updates. To the best of our knowledge, this is the first work to convert a pretrained AR video diffusion model into a hybrid linear attention architecture, through an efficient two-stage training scheme for AR video. With 75% of layers replaced by hybrid linear attention, the model achieves up to 2.26 wall-clock speedup and 54% memory reduction, while maintaining comparable quality with improving temporal consistency.

Kunyang Li, Mubarak Shah, Yuzhang Shang

Institute of Artificial Intelligence, University of Central Florida

Memory-Augmented Neural Networks Video Diffusion Models Self-Attention Linear Attention Autoregressive Video Generation Diffusion Model Inference Acceleration+1

May 13, 2026cs.LG

QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits scalability to long contexts. State-space models (SSMs) provide an efficient alternative with linear-time computation by evolving a latent state through recurrent updates, but their memory is typically formed via additive or linear transitions, which can limit their ability to capture complex global interactions across tokens. In this work, we introduce one of the first studies to leverage the superposition property of quantum systems to enhance state-based sequence modeling. In particular, we propose Quantum Long-Attention Memory (QLAM), a hybrid quantum-classical memory mechanism that can be viewed as a quantum extension of state-space models. Instead of maintaining a classical latent state updated through additive dynamics, QLAM represents the hidden state as a quantum state whose amplitudes encode a superposition of historical information. The state evolves through parameterized quantum circuits conditioned on the input, enabling a non-classical, globally update mechanism. In this way, QLAM preserves the recurrent and linear-time structure of SSMs while fundamentally enriching the memory representation through quantum superposition. Unlike attention mechanisms that explicitly compute pairwise interactions, QLAM implicitly captures global dependencies through the evolution of the quantum state, and retrieves task-relevant information via query-dependent measurements. We evaluate QLAM on sequential variants of standard image classification benchmarks, including sMNIST, sFashion-MNIST, and sCIFAR-10, where images are flattened into token sequences. Across all tasks, QLAM consistently improves over recurrent baselines and transformer-based models.

Hoang-Quan Nguyen, Sankalp Pandey, Khoa Luu

Department of Electrical Engineering and Computer Science, University of Arkansas, AR · Quantum AI Lab, University of Arkansas, AR

Memory-Augmented Neural Networks Hybrid Quantum-Classical ML Sequence Modeling Quantum Neural Networks

May 13, 2026cs.LG

Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory

For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for language modeling due to catastrophic gradient instability during Backpropagation Through Time. In this work, we break this stalemate with \textit{Phasor Memory Network} (PMNet), a novel architecture that structurally resolves memory volatility through \textit{Unitary Phasor Dynamics} and \textit{Hierarchical Learnable Anchors}. Rather than relying on brute-force scaling, we present a mechanistic proof-of-concept in a controlled byte-level setting. By constraining recurrent state updates to phase rotations on a complex unit circle, PMNet preserves gradient norms and inherently prevents divergence without the need for specialized initialization. We empirically demonstrate the active actuation of the memory module through a synthetic Copy-Paste task, where PMNet utilizes an expansive \textit{85-slot hierarchical memory tree} (

=\sum^{4}_{h=1}4^{h-1}

) to achieve near 100% exact retrieval across temporal distances that completely exceed the local sliding window attention's receptive field. Furthermore, despite being a compact 119M parameter model trained on 18.8B tokens, PMNet matches the zero-shot long-context robustness of a Mamba model that is three times larger. Our ablation studies and gradient analyses confirm that the historical failure of explicit memory was a structural alignment problem, which PMNet effectively overcomes, providing a theoretically grounded foundation for scalable sequence modeling.

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

College of Pharmacy Chungnam National University Daejeon, South Korea · Department of Computer Science & Engineering Chungnam National University Daejeon, South Korea

Memory-Augmented Neural Networks Memory-Augmented Language Models Long-Context Language Modeling Persistent Memory for Language Models Recurrent Neural Networks Memorization in Generative Models

May 13, 2026cs.LG

PaMM: Periodic Motif Memory for Atomistic Models with an Explicit Local-Structure Interface

Periodic crystals repeatedly instantiate similar local coordination motifs across translated cells and chemically related structures, but current equivariant atomistic models usually encode these patterns only implicitly in dense edge features. We introduce PaMM, a periodic motif memory that augments the UMA eSCN-MD edge encoder with explicit pair and triplet lookup features. Pair motifs are keyed by

(Z_j, Z_i, b_r)

and triplet motifs by

(Z_j, Z_i, Z_k, b_θ)

, hashed into fixed-size tables and fused with the baseline edge representation through lightweight gate-only and affine-equipped variants. We evaluate PaMM in a matched UMA-S OMAT setting and focus on a narrow question: whether explicit motif memory helps at a fixed intermediate training budget. At the 10k-step checkpoint, both PaMM variants improve over the plain baseline; gate-only gives the best energy MAE, while the affine-equipped variant gives the best force MAE. A matched 20k follow-up keeps the same operating-point picture. Aligned controls show that the gain weakens for pair-only, triplet-only, random-bucket, and parameter-matched MLP alternatives, suggesting that the benefit is tied to structured pair/triplet organization rather than generic added capacity. A within-OMAT24 source-family evaluation also shows small but consistent gains across held-out generation families. We therefore make a focused claim: in the studied UMA-S + OMAT regime, explicit pair/ triplet motif memory is a useful inductive bias for periodic atomistic modeling. We do not claim broad cross-dataset transfer, a uniquely preferred fusion variant, or strong scientific interpretability beyond a more inspectable local-structure interface.

Ryan Dong

Independent Research

Memory-Augmented Neural Networks Machine Learning Interatomic Potentials Associative Memory

May 13, 2026cs.LG

McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting

Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. However, such an approach accumulates errors over long rollouts, causing forecasts to drift away from physically plausible evolution trajectories. Although various studies have attempted to alleviate this problem by improving step-wise prediction accuracy, they largely neglect the global temporal evolution of meteorological systems and lack mechanisms to actively correct drift during rollouts. To address this issue, we propose McCast, a memory-guided latent drift correction method for precipitation nowcasting. Rather than treating memory as an unordered dictionary of latent states for passive conditioning, McCast leverages temporally organized memory to actively correct autoregressive latent evolution. Specifically, McCast introduces a Drift-Corrective Memory Bank (DCBank) that explicitly estimates the temporally consistent drift corrections to calibrate the divergent trajectory. DCBank performs drift correction in two stages: a Corrective Latent Extractor first predicts an initial correction from the current prediction and a reference latent state, and a Correction-Aware Memory Retrieval module then refines the initial correction using temporally organized historical memory. By explicitly correcting latent evolution, instead of improving step-wise prediction accuracy only, McCast produces more temporally coherent and reliable long-horizon forecasts. Experiments on two widely used benchmarks, SEVIR and MeteoNet, show that McCast achieves state-of-the-art performance, particularly in challenging long-horizon forecasting scenarios.

Penghui Wen, Yu Luo, Lintao Wang +4

School of Computer Science, The University of Sydney, Australia · School of Life and Environmental Science, The University of Sydney, Australia

Memory-Augmented Neural Networks Precipitation Forecasting Precipitation Nowcasting Autoregressive Modeling

May 13, 2026cs.CV

Does Engram Do Memory Retrieval in Autoregressive Image Generation?

The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretraining, with the appealing interpretation that it provides a content-addressed shortcut to recurring local token patterns. We ask whether this interpretation transfers to autoregressive (AR) image generation, or whether the observed gains, if any, come from a different mechanism. We adapt the Engram module to vision with 2D spatial

n

-gram hashing, gated fusion, and KV-cache-compatible incremental inference, and inject it into a class-conditional AR generator trained on ImageNet 256x256. Across a sweep of backbone-to-memory budget ratios

ρ{\in}[0.17, 0.90]

, every Engram-augmented variant trails the pure AR baseline in FID, indicating that the module saves backbone FLOPs but does not, by itself, improve sample quality. We then probe how the module is used. A gate-clamp sweep shows that disabling the Engram pathway entirely is catastrophic, yet a tiny constant gate (g=0.10) matches or beats the learned gate -- inconsistent with a heavily content-addressed recall mechanism. A donor-probe experiment shows that swapping the hash inputs for matched, adversarial, or random same-class exemplars produces statistically indistinguishable next-token distributions, while collapsing or randomising the table degrades them by two to three orders of magnitude. Finally, training a model from scratch with the entire memory table frozen to

\mathcal{N}(0, 1)

noise costs only

Δ\text{FID}{=}0.10

and actually raises Inception Score. Together, these findings indicate that the Engram in AR image generation behaves not as a content-addressed retriever but as a gated architectural side-pathway: a hash-keyed residual stream whose benefit is dominated by the pathway itself, with the learned table contributing only a small distributional refinement.

Jinghao Wang, Qiyuan He, Chunbin Gu +1

1The Chinese University of Hong Kong · 2National University of Singapore

Memory-Augmented Neural Networks Image Generation Autoregressive Image Generation Associative Memory

May 11, 2026cs.CL

Mela: Test-Time Memory Consolidation based on Transformation Hypothesis

Memory consolidation, the process by which transient experiences are transformed into stable, structured representations, is a foundational organizing principle in the human brain, yet it remains largely unexplored as a design principle for modern sequence models. In this work, we leverage established neuroscientific theories of memory consolidation and cross-frequency coupling to propose the Hierarchical Memory Module (HMM), a neural memory architecture composed of two functionally distinct sub-modules that operate at different update frequencies. Inspired by the transformation hypothesis, the low-frequency sub-module produces high-level representations that capture abstract, gist-level knowledge, while the high-frequency sub-module produces fine-grained representations that preserve richer episodic detail. The final memory output is dynamically reconstructed as a context-dependent combination of both representations, analogous to the reconstructive nature of human memory retrieval. We integrate HMM into a Transformer-based language decoder to form Mela, a family of memory-augmented language models that perform online memory consolidation at test time. To further exploit the multi-granularity memory representations produced by HMM, we introduce MemStack, a method that distributes different levels of memory features across the early layers of the decoder without introducing additional tokens. Experiments on language modeling demonstrate that Mela outperforms Transformer baselines across all the model sizes. Moreover, with the pretrained context length fixed at 4K, Mela maintains performance on significantly longer contexts, whereas Transformer baselines degrade rapidly beyond their training length. Extensive ablation studies validate the contribution of each component and provide guidance for practical configuration.

Lungchuan Chen

MusubiAI

Memory-Augmented Neural Networks Memory-Augmented Language Models Long-Context Language Modeling

May 8, 2026cs.LG

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficiency by restricting each layer update to a fixed low-rank form, but this static parameterization can be too rigid when the appropriate correction depends on the input and on the evolving depth-wise computation of the network. Our approach replaces a purely layer-local adapter with a shared queryable memory of low-rank update atoms. For each block of layers, the model forms a query from the current low-rank state and a running summary of previous blocks, uses this query to retrieve a content-dependent combination of shared update components via attention, and applies the resulting routed operator within the low-rank bottleneck. In this way, the method retains the efficiency and scalability of low-rank adaptation while allowing the effective update to vary across inputs and to share reusable structure across layers. The resulting architecture provides a principled middle ground between static LoRA-style updates and fully generated parameter updates: it remains compact and parameter-efficient while supporting dynamic, context-sensitive adaptation. Further, we incorporate instruction-regularization by augmenting routing logits with a language-induced prior over update atoms, thereby biasing the selection of low-rank transformations toward semantically relevant directions without generating unconstrained parameter updates. Experiments on noisy non-linear regression tasks and LLM fine-tuning suggest that this queryable update-memory formulation can improve final test performance and training stability compared to standard low-rank adaptation, while using a comparable number of trainable parameters.

Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho +1

Department of Computer Science University of Texas at Austin · Department of Government University of Texas at Austin · University of Texas at Austin

Memory-Augmented Neural Networks Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

May 4, 2026cs.AI

The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence

Contemporary artificial intelligence systems achieve strong performance through large-scale parameterization, retrieval augmentation, and training on extensive static corpora. Despite these advances, they continue to face limitations in persistent memory, temporal grounding, provenance, and interpretability. These challenges are especially pronounced in large language models, where experience is encoded implicitly in fixed parameters, limiting the ability to preserve, inspect, and reinterpret past interactions over time. This paper establishes a memory-centric architectural foundation for artificial intelligence in which experience is represented explicitly and persistently to support temporal grounding, provenance, and interpretability. It proposes an alternative to parameter-centric approaches by treating memory as a first-class, structured substrate for reasoning. We introduce the Dynamic Gist-Based Memory Model (DGMM), an architecture in which experience is represented as an evolving, graph-structured episodic-semantic memory. DGMM encodes experience as interconnected conceptual structures grounded in time, source, and interaction context, and defines selective, cue-conditioned recall as the mechanism for constructing working memory. A formal schema and architectural invariants are provided based on additive memory growth and recall-conditioned interpretation. The results specify properties of DGMM, including episodic persistence, locality of cue-conditioned surprise, and contextual variability without structural modification of stored memory. DGMM provides a coherent architectural theory in which memory is explicit and persistent, supporting evolving interpretation without retraining and enabling interpretable, context-aware, and temporally grounded AI systems.

Terry Dorsey, Kevin Huggins

Harrisburg University of Science and Technology, USA

Memory-Augmented Neural Networks LLM Interpretability LLM Memory Episodic Memory

Apr 26, 2026cs.LG

Graph Memory Transformer (GMT)

We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while preserving the surrounding autoregressive architecture. The proposed Graph Memory Transformer (GMT) keeps causal self-attention intact, but replaces the usual per-token FFN transformation with a memory cell that routes token representations over a learned bank of centroids connected by a learned directed transition matrix. In the base GMT v7 instantiation studied here, each of 16 transformer blocks contains 128 centroids, a 128 * 128 edge matrix, gravitational source routing, token-conditioned target selection, and a gated displacement readout. The cell therefore returns movement from an estimated source memory state toward a target memory state, rather than a retrieved value. The resulting model is a fully decoder-only language model with 82.2M trainable parameters and no dense FFN sublayers, compared with a 103.0M-parameter dense GPT-style baseline used in the evaluation. The base v7 model trains stably and exposes centroid usage, transition structure, and source-to-target movement as directly inspectable quantities of the forward computation. It remains behind the larger dense baseline in validation loss and perplexity (3.5995/36.58 vs. 3.2903/26.85), while showing close zero-shot benchmark behavior under the evaluated setting. These results are not intended as a state-of-the-art claim; they support the viability and structural interpretability of replacing dense within-token transformation with graph-mediated memory navigation. Broader scaling, optimized kernels, and more extensive benchmark evaluation are left for subsequent work.

Nicola Zanarini, Niccolò Ferrari, Evelina Lamma

Bonfiglioli Engineering s.r.l. · Department of Engineering, University of Ferrara, Via Saragat 1, 44122 Ferrara, Italy · NAIS s.r.l., Via Maria Callas 4, 40131 Bologna, Italy

Memory-Augmented Neural Networks Transformer FFNs Graph Neural Networks Memory-Augmented Language Models Transformer Decoder-Only Language Models

Apr 25, 2026cs.IR

A Parametric Memory Head for Continual Generative Retrieval

Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries. While this model-as-index paradigm offers architectural simplicity, it is poorly suited to dynamic document collections. Unlike modular systems, where indexes are easily updated, GenIR's knowledge is parametrically encoded in its weights; consequently, standard adaptation methods such as full and parameter-efficient fine-tuning can induce catastrophic forgetting. We show that sequential adaptation improves retrieval on newly added documents but substantially degrades performance on earlier slices, exposing a pronounced stability-plasticity trade-off. To address this, we propose post-adaptation memory tuning (PAMT), a memory-only stabilization stage that augments an adapted model with a modular parametric memory head (PMH). PAMT freezes the backbone and attaches a product-key memory with fixed addressing. During prefix-trie constrained decoding, decoder hidden states sparsely query PMH to produce residual corrections in hidden space; these corrections are mapped to score adjustments via the frozen output embedding matrix, computed only over trie-valid tokens. This guides docid generation while keeping routing and backbone parameters fixed. To limit cross-slice interference, PAMT updates only a fixed budget of memory values selected using decoding-time access statistics, prioritizing entries frequently activated by the current slice and rarely used in prior sessions. Experiments on MS MARCO and Natural Questions under sequential, disjoint corpus increments show that PAMT substantially improves retention on earlier slices with minimal impact on retrieval performance for newly added documents, while modifying only a sparse subset of memory values per session.

Kidist Amde Mekonnen, Yubao Tang, Maarten de Rijke

University of Amsterdam Amsterdam, The Netherlands

Memory-Augmented Neural Networks LLM Memory Generative Retrieval Catastrophic Forgetting

Apr 23, 2026cs.LG

Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning

We study learned memory tokens as a computational scratchpad for a single-block Universal Transformer with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. Memory tokens are empirically necessary: no configuration without them reaches non-trivial performance. The optimal count has a sharp lower threshold (T=0 always fails, T=8 reliably succeeds) followed by a stable plateau (T=8-32, 57.4% +/- 0.7% exact-match) and a dilution boundary at T=64. Under halt-side pressure (lambda warmup), mean halt drops monotonically with memory size across the plateau (from 11.6 at T=8 to 8.3 at T=64), showing that memory tokens and ponder depth substitute as resources at fixed accuracy. We also identify a router initialization trap that causes the majority of training runs to fail: both default zero-bias and Graves' recommended positive bias settle into a shallow halt equilibrium the model cannot escape. Inverting the bias to -3 ("deep start") eliminates the failure mode, and ablation shows the trap is inherent to ACT initialization rather than an artifact of our architecture. With reliable training, ACT yields an order of magnitude lower seed variance than fixed-depth processing (+/-0.7 vs +/-9.3 pp); lambda warmup recovers 34% of compute at matched accuracy; and attention heads specialize into memory readers, constraint propagators, and integrators across recursive depth. Code: https://github.com/che-shr-cat/utm-jax.

Grigory Sapunov

Intento

Memory-Augmented Neural Networks Recurrent Transformers Algorithmic Reasoning Adaptive Computation

Apr 22, 2026cs.MM

Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction

Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as content recommendation and traffic allocation. In real-world scenarios, it is critical for MVPP approaches to understand both the temporal dynamics of a given video (temporal) and its historical relevance to other videos (spatial). However, existing approaches sufer from limitations in both dimensions: temporally, they rely on sparse short-range sampling that restricts content perception; spatially, they depend on flat retrieval memory with limited capacity and low efficiency, hindering scalable knowledge utilization. To overcome these limitations, we propose a unified framework that achieves joint spatio-temporal enlargement, enabling precise perception of extremely long video sequences while supporting a scalable memory bank that can infinitely expand to incorporate all relevant historical videos. Technically, we employ a Temporal Enlargement driven by a frame scoring module that extracts highlight cues from video frames through two complementary pathways: sparse sampling and dense perception. Their outputs are adaptively fused to enable robust long-sequence content understanding. For Spatial Enlargement, we construct a Topology-Aware Memory Bank that hierarchically clusters historically relevant content based on topological relationships. Instead of directly expanding memory capacity, we update the encoder features of the corresponding clusters when incorporating new videos, enabling unbounded historical association without unbounded storage growth. Extensive experiments on three widely used MVPP benchmarks demonstrate that our method consistently outperforms 11 strong baselines across mainstream metrics, achieving robust improvements in both prediction accuracy and ranking consistency.

Dali Wang, Yunyao Zhang, Junqing Yu +3

Huazhong University of Science and Technology Wuhan, China · La Trobe University Melbourne, Australia · Beijing Institute of Computer Technology and Applications Beijing, China

Social Media Analysis Memory-Augmented Neural Networks Temporal Video Understanding

Apr 20, 2026eess.AS

MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation

Speech-based automatic estimation of depression levels is essential for enabling early detection and timely intervention, particularly in resource-constrained mental health settings. In recent years, deep learning has demonstrated impressive success across various domains, including affective computing and mental health assessment. Most existing approaches rely on RNN-based architectures (such as LSTM and GRU) to model temporal information for depression estimation. However, the extracted features often emphasize only a few adjacent speech segments, limiting their ability to capture long-range dependencies. To overcome this limitation, we introduce a memory-based feature augmentation method that enhances the representational capacity of GRU-extracted features. Rather than indiscriminately incorporating historical data, our memory bank is designed to selectively integrate two types of components in order to reduce redundancy and irrelevance: (1) historical temporal features that closely resemble the current GRU output, offering complementary contextual information; and (2) dynamic memory features identified based on feature variability, which capture behavioral and emotional fluctuations indicative of depressive symptoms. To effectively fuse the memory-augmented features with GRU outputs, we further design a Hierarchical Attention Fusion (HAF) module. Our method is evaluated on the widely used DAIC-WOZ and E-DAIC datasets, achieving state-of-the-art performance.

Xuzhi Wang, Xinran Wu, Ziping Zhao +2

School of Computer and Information Engineering, Tianjin Normal University (TJNU), Tianjin 300387, China · Department of Automation, Tsinghua University, Beijing 100084, China · Chair of Health Informatics, Technical University of Munich, Munich, Germany +1

Memory-Augmented Neural Networks Depression Detection Depression Severity Estimation

Feb 12, 2026cs.LG

RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State

Linear attention offers an efficient alternative to full attention with a fixed-size recurrent state. However, this state is shared by all tokens, so information from distinct tokens becomes superposed within it and produces inter-token interference that degrades long-range fine-grained recall. To address this issue, we propose RAM-Net, which replaces dense access to a shared state with sparse address-based access. RAM-Net organizes the recurrent state as a fixed-size array of independent slots and uses an Address Decoder that maps each key or query into a sparse address, selecting a small subset of slots to write to or read from at each step. This design directs tokens with non-overlapping addresses to disjoint slots, suppressing inter-token interference, while keeping per-step state access dependent only on the number of selected slots rather than the total state size. Empirically, RAM-Net outperforms strong recurrent baselines on fine-grained long-range retrieval and achieves the lowest perplexity with competitive commonsense reasoning. It does so while accessing fewer state elements per step than all baselines, e.g.,

8\times

fewer than Mamba2.

Kaicheng Xiao, Haotian Li, Liran Dong +1

The Chinese University of Hong Kong

Memory-Augmented Neural Networks Long-Context Language Modeling Linear Attention Associative Memory