SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography

• URL: http://arxiv.org/abs/2506.12356v2
• Date: Sat, 01 Nov 2025 17:33:29 GMT
• Title: SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography
• Abstract summary: Surface electromyography (sEMG) at the wrists could enable natural, keyboard-free text entry.<n>State-of-the-art emg2qwerty baseline still misrecognizes $51.8%$ of characters in the zero-shot setting on unseen users.<n>We trace many of these errors to mismatched cross-user signal statistics.
• Score: 3.3640830721676003
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Surface electromyography (sEMG) at the wrists could enable natural, keyboard-free text entry, yet the state-of-the-art emg2qwerty baseline still misrecognizes $51.8\%$ of characters in the zero-shot setting on unseen users and $7.0\%$ after user-specific fine-tuning. We trace many of these errors to mismatched cross-user signal statistics, fragile reliance on high-order feature dependencies, and the absence of architectural inductive biases aligned with the bilateral nature of typing. To address these issues, we introduce three simple modifications: (i) Rolling Time Normalization, which adaptively aligns input distributions across users; (ii) Aggressive Channel Masking, which encourages reliance on low-order feature combinations more likely to generalize across users; and (iii) a Split-and-Share encoder that processes each hand independently with weight-shared streams to reflect the bilateral symmetry of the neuromuscular system. Combined with a five-fold reduction in spectral resolution ($33\!\rightarrow\!6$ frequency bands), these components yield a compact Split-and-Share model, SplashNet-mini, which uses only $\tfrac14$ the parameters and $0.6\times$ the FLOPs of the baseline while reducing character-error rate (CER) to $36.4\%$ zero-shot and $5.9\%$ after fine-tuning. An upscaled variant, SplashNet ($\tfrac12$ the parameters, $1.15\times$ the FLOPs of the baseline), further lowers error to $35.7\%$ and $5.5\%$, representing relative improvements of $31\%$ and $21\%$ in the zero-shot and fine-tuned settings, respectively. SplashNet therefore establishes a new state of the art without requiring additional data.

Related papers

• Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs [43.01574038234673]
  Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count.<n>We show that this recipe breaks for speech large language models (speech-LLMs), when the acoustic encoder and the language decoder differ by an order of magnitude in update norm.
  arXiv  Detail & Related papers  (2026-09-10T16:17:19Z)
• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors [51.56484100374058]
  Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against.<n>We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag.<n>We show that this bidirectionality supplies a measurement-free test-time error signal.
  arXiv  Detail & Related papers  (2026-08-01T13:49:46Z)
• Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders [9.291632832739822]
  We introduce two sparsity regularizers compatible with the Top-$k$ architecture.<n>Our central finding is that hard architectural sparsity and soft sparsity regularization are complementary rather than mutually exclusive.
  arXiv  Detail & Related papers  (2026-06-25T17:34:39Z)
• Characterization of nested Walsh parity-check filters in a single-photon eight-mode register on a cloud photonic processor [0.0]
  We characterize two nested Walsh parity-check filters implemented on Quandela's Belenos cloud photonic processor.<n>Across more than 340,000 detections, neutral inputs show residual DC-port leakage of $0.02%$-$1.1%$.<n>A sector-preserving unitary core keeps leakage far below non-neutral controls over one to three applications.
  arXiv  Detail & Related papers  (2026-06-16T19:01:47Z)
• Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization [58.14514930760722]
  We consider a decentralized setup in which the participants collaboratively train and serve a large neural network.<n>In this setup, we explore the possibility of unmaterializable weights, where a full weight set is never available to any one participant.<n>We introduce Unextractable Protocol Models (UPMs): a training and inference framework that leverages the sharded model setup.
  arXiv  Detail & Related papers  (2026-05-22T10:24:57Z)
• Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes [53.726365933748134]
  We analyze a negative weight drift induced by the interaction between standard losses and positively biased activation functions.<n>We characterize the sparsity-accuracy tradeoff across 79 configurations and identify a sharp accuracy cliff above $sim$70% activation sparsity.
  arXiv  Detail & Related papers  (2026-05-17T21:29:20Z)
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation [50.55853275866995]
  Real-time interactive video generation requires low-latency, streaming, and controllable rollout.<n>In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps.<n>We propose textbfCausal Forcing++, a principled and scalable pipeline.
  arXiv  Detail & Related papers  (2026-05-14T17:46:36Z)
• Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating [0.6945765172815976]
  Gated-SwinRMT is a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT)<n>Gated-SwinRMT-SWAT substitutes softmax with sigmoid activation, implements balanced ALiBi slopes with multiplicative post-activation spatial decay, and gates the value projection via SwiGLU.<n>Gated-SwinRMT-Retention retains softmax-normalized retention with an additive log-space decay bias and incorporates an explicit G1 sigmoid gate
  arXiv  Detail & Related papers  (2026-04-07T16:12:31Z)
• Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency [61.68376148916503]
  We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.<n>Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains.<n>We evaluate six model configurations -- GPT-Realtime, Gemini Live 2.5, Gemini Live 3.1, Grok, Ultravox v0.7, and a traditional Cascaded pipeline (Whisper$rightarrow$rightarrow$TTS) -- across accuracy, latency, and turn-
  arXiv  Detail & Related papers  (2026-04-06T16:46:52Z)
• Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities [3.1861308132183375]
  Radial Mntz-Szsz Networks (RMN) represent fields as linear combinations of learnable radial powers $r$, including negative exponents.<n>RMN achieves 1.5$times$-51$times$ lower RMSE than coordinates and 10$times$--100$times$ lower RMSE than SIREN.
  arXiv  Detail & Related papers  (2026-02-09T09:25:37Z)
• Optimized Measurement Schedules for the Surface Code with Dropout [0.10279607451688234]
  Recent work has shown that fabrication defects can be well-handled using a strategy relying on the mid-error-correction-cycle state.<n>We quantify the impact of the choice of a more complete set of gauge operators, as well as a new method for excising effectively unused qubits.
  arXiv  Detail & Related papers  (2025-12-11T18:02:39Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net [0.0]
  We propose a spectrally normalized surrogate for forward and inverse mechanical homogenization with hard physical guarantees.<n>In 3D linear elasticity on an open dataset of biphasic microstructures, a fully connected Voigt-Reuss net trained on $>!7.5times 105$ FFT-based labels with 236 isotropy-in descriptors.<n>Overall, the Voigt-Reuss net unifies accurate, physically admissible forward prediction with large-batch, constraint-consistent inverse design.
  arXiv  Detail & Related papers  (2025-11-14T15:17:37Z)
• Hierarchical Federated Graph Attention Networks for Scalable and Resilient UAV Collision Avoidance [0.5505634045241287]
  Real-time performance, adversarial resiliency, and privacy preservation are the most important metrics that need to be balanced to practice collision avoidance.<n>We have proposed an adaptive differential privacy mechanism, wherein the noise level $(in [0.1, 1.0])$ is dynamically reduced based on an evaluation of the measured real-time threat.<n>This architecture provides a scalable scenario of 500 UAVs with a collision rate of $ 2.0%$ and the Byzantine fault tolerance of $f n/3$.
  arXiv  Detail & Related papers  (2025-11-05T12:01:00Z)
• A3 : an Analytical Low-Rank Approximation Framework for Attention [14.649496050074735]
  We propose $tt Attt 3$, a post-training low-rank approximation framework.<n>We show that $tt Attt 3$ maintains superior performance compared to SoTAs.<n>We also demonstrate the versatility of $tt Att 3$, including KV cache compression, quantization, and mixed-rank assignments for enhanced performance.
  arXiv  Detail & Related papers  (2025-05-19T10:29:32Z)
• Simple ReFlow: Improved Techniques for Fast Flow Models [68.32300636049008]
  Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps. We propose seven improvements for training dynamics, learning and inference. We achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs.
  arXiv  Detail & Related papers  (2024-10-10T11:00:55Z)
• $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence [7.0479532872043755]
  $t3$VAE is a modified VAE framework that incorporates Student's t-distributions for the prior, encoder, and decoder. We show that $t3$VAE significantly outperforms other models on CelebA and imbalanced CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2023-12-02T13:14:28Z)
• (Private) Kernelized Bandits with Distributed Biased Feedback [13.312928989951505]
  We study kernelized bandits with distributed biased feedback. New emphdistributed phase-then-batch-based elimination (textttDPBE) algorithm is proposed. We show that textttDPBE achieves a sublinear regret of $tildeO(T1-alpha/2+sqrtgamma_T T)$, where $alphain (0,1)$ is the user-sampling parameter one can tune.
  arXiv  Detail & Related papers  (2023-01-28T02:30:15Z)
• From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets [7.812210699650151]
  We replace the first-layer combination "real-valued convolutions + max pooling" We claim that CMod and RMax produce comparable outputs when the convolution kernel is band-pass and oriented. Our approach achieves superior accuracy on ImageNet and CIFAR-10 classification tasks.
  arXiv  Detail & Related papers  (2022-12-01T09:42:55Z)
• FeDXL: Provable Federated Learning for Deep X-Risk Optimization [105.17383135458897]
  We tackle a novel federated learning (FL) problem for optimizing a family of X-risks, to which no existing algorithms are applicable. The challenges for designing an FL algorithm for X-risks lie in the non-decomability of the objective over multiple machines and the interdependency between different machines.
  arXiv  Detail & Related papers  (2022-10-26T00:23:36Z)
• Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP [52.25478388220691]
  Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks. They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers. We propose a new positional spacial gating unit (PoSGU) to efficiently encode the cross-token relations for token mixing.
  arXiv  Detail & Related papers  (2022-07-15T04:18:06Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask [11.067931264340931]
  Federated learning alleviates the privacy risk in distributed learning by transmitting only the local model updates to the central server. Previous works have tackled these challenges by combining personalization with model compression schemes including quantization and pruning. We propose HideNseek which employs one-shot data-agnostic pruning to get a subnetwork based on weights' synaptic saliency.
  arXiv  Detail & Related papers  (2022-06-09T09:55:31Z)
• Rethinking Dilated Convolution for Real-time Semantic Segmentation [0.0]
  We take a different approach by using dilated convolutions with large dilation rates throughout the backbone. Our model RegSeg achieves competitive results on real-time Cityscapes and CamVid datasets.
  arXiv  Detail & Related papers  (2021-11-18T22:08:21Z)
• R-Drop: Regularized Dropout for Neural Networks [99.42791938544012]
  Dropout is a powerful and widely used technique to regularize the training of deep neural networks. We introduce a simple regularization strategy upon dropout in model training, namely R-Drop, which forces the output distributions of different sub models to be consistent with each other.
  arXiv  Detail & Related papers  (2021-06-28T08:01:26Z)
• 1$\times$N Block Pattern for Network Sparsity [90.43191747596491]
  We propose one novel concept of $1times N$ block sparsity pattern (block pruning) to break this limitation. Our pattern obtains about 3.0% improvements over filter pruning in the top-1 accuracy of MobileNet-V2. It also obtains 56.04ms inference savings on Cortex-A7 CPU over weight pruning.
  arXiv  Detail & Related papers  (2021-05-31T05:50:33Z)
• Large-time asymptotics in deep learning [0.0]
  We consider the impact of the final time $T$ (which may indicate the depth of a corresponding ResNet) in training. For the classical $L2$--regularized empirical risk minimization problem, we show that the training error is at most of the order $mathcalOleft(frac1Tright)$. In the setting of $ellp$--distance losses, we prove that both the training error and the optimal parameters are at most of the order $mathcalOleft(e-mu
  arXiv  Detail & Related papers  (2020-08-06T07:33:17Z)

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.