The Von-Neumann State-Space Transformer for neural decoding

• URL: http://arxiv.org/abs/2608.25088v1
• Date: Tue, 25 Aug 2026 19:28:33 GMT
• Title: The Von-Neumann State-Space Transformer for neural decoding
• Abstract summary: Cortical computation is strikingly low-dimensional.<n>We introduce a memory-augmented Transformer whose feed-forward block is a low-rank instruction bank.<n>VN-SST is far more data-efficient than a modern Transformer.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cortical computation is strikingly low-dimensional: a handful of latent variables, carried in a neural population's activity, steer the higher-dimensional responses of individual neurons. Our aim is sample efficiency-models that decode well from limited data and at small parameter budgets. In a standard Transformer layer, the feed-forward block applies the same operator to every token. We suggest a von-Neumann inspired hypothesis of efficient computation as an alternative for neural decoding: a controller decodes an instruction and then executes a token-specific operator; the usual realization-a soft mixture of experts-only blends their outputs, not operators. We introduce a von-Neumann State-Space Transformer (VN-SST), a memory-augmented Transformer whose feed-forward block is a low-rank instruction bank: a shared base operator plus a small set of learned low-rank instructions, from which a per-token code synthesizes the weight matrix actually used at that token. The code is read from a low- dimensional projection of a carried state-space memory, so a slow latent trajectory acts as an instruction pointer-mirroring how low-dimensional dynamics may route cortical computation. On three motor-cortex neural-decoding benchmarks, VN-SST is far more data-efficient than a modern Transformer, each jointly predicting spikes and decoding behavior. This model wins by a wide margin on the scarcest benchmark, leads on the other two, and turns longer context into rising rather than falling accuracy. We evaluated that the network compresses a large instruction bank to a few bits per token, so program capacity acts as a control channel, not an accuracy lever. The same model is also more parameter-efficient on two small text benchmarks used for language modeling (LLMs), suggesting a generic mechanism.

Related papers

• Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces [7.820614736576814]
  We study operator learning using encoder--decoder neural networks.<n>We introduce a variation space as an infinite-dimensional structural class for nonlinear operators.<n>For operators in this space, we establish approximation bounds for encoder--decoder two-layer networks in the Bochner $Lq$ norm.
  arXiv  Detail & Related papers  (2026-05-31T13:53:17Z)
• qecGPT: decoding Quantum Error-correcting Codes with Generative Pre-trained Transformers [5.392298820599664]
  We propose a framework for decoding quantum error-correcting codes with generative modeling. We use autoregressive neural networks, specifically Transformers, to learn the joint probability of logical operators and syndromes. Our framework is general and can be applied to any error model and quantum codes with different topologies.
  arXiv  Detail & Related papers  (2023-07-18T07:34:02Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Predicting Attention Sparsity in Transformers [0.9786690381850356]
  We propose Sparsefinder, a model trained to identify the sparsity pattern of entmax attention before computing it. Our work provides a new angle to study model efficiency by doing extensive analysis of the tradeoff between the sparsity and recall of the predicted attention graph.
  arXiv  Detail & Related papers  (2021-09-24T20:51:21Z)
• Sentence Bottleneck Autoencoders from Transformer Language Models [53.350633961266375]
  We build a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a generative, denoising one, while only training a sentence bottleneck and a single-layer modified transformer decoder. We demonstrate that the sentence representations discovered by our model achieve better quality than previous methods that extract representations from pretrained transformers on text similarity tasks, style transfer, and single-sentence classification tasks in the GLUE benchmark, while using fewer parameters than large pretrained models.
  arXiv  Detail & Related papers  (2021-08-31T19:39:55Z)
• CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation [12.005340904206697]
  CANINE is a neural encoder that operates directly on character sequences without explicit tokenization or vocabulary. CanINE outperforms a comparable mBERT model by >= 1 F1 on TyDi QA, a challenging multilingual benchmark.
  arXiv  Detail & Related papers  (2021-03-11T18:57:44Z)
• RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection [85.44877328116881]
  We present a novel neural network for symbol detection in wireless communication systems. It is motivated by several important considerations in wireless communication systems. We compare its performance against existing methods and the results show the ability of our network to efficiently handle a variable number of transmitters.
  arXiv  Detail & Related papers  (2020-06-30T22:43:01Z)
• Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing [112.2208052057002]
  We propose Funnel-Transformer which gradually compresses the sequence of hidden states to a shorter one. With comparable or fewer FLOPs, Funnel-Transformer outperforms the standard Transformer on a wide variety of sequence-level prediction tasks.
  arXiv  Detail & Related papers  (2020-06-05T05:16:23Z)
• Learning to Encode Position for Transformer with Continuous Dynamical Model [88.69870971415591]
  We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. We model the evolution of encoded results along position index by such a dynamical system.
  arXiv  Detail & Related papers  (2020-03-13T00:41:41Z)

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.