Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation

• URL: http://arxiv.org/abs/2606.18315v1
• Date: Tue, 16 Jun 2026 11:23:30 GMT
• Title: Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation
• Abstract summary: This article proposes Ghost Attractor Networks, a theoretically derived dynamical decoder.<n>It evolves under a learned potential with drift and produces a basin-attractor structure by construction.
• Score: 15.734979840846568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential output generation with large-scale Transformer and diffusion decoders pays a memory cost that grows with sequence length, plus iterative per-step computation. Replacing them with small feed-forward decoders restores efficiency but produces unstructured latent representations that limit closed-loop control: phase-conditioned action generation and cross-step latent carry-over both require a latent geometry with stable basins. This article proposes Ghost Attractor Networks, a theoretically derived dynamical decoder whose latent evolves under a learned potential with drift and produces a basin-attractor structure by construction. Three desiderata (multi-modality, decoder-level single-pass switching, and constant memory) motivate the potential-drift form, and mode transitions arise as saddle-node bifurcations with ghost-attractor escape. A hierarchical phase-space decomposition separates first-order basin convergence from second-order proprioceptive refinement. Empirically, a Ghost trained end-to-end with a behavioral-cloning and contrastive objective exhibits the predicted gradient-flow contraction in its potential, with the gradient norm decaying by 67 percent across five integration steps on 1430 held-out samples. Ghost is evaluated as a robotic action decoder. A 2.3-million-parameter Ghost matches the offline accuracy of a 1.07-billion-parameter Diffusion Transformer at 462 times fewer parameters and 32 times lower latency, and beats five alternative 2M-parameter decoders (MLP, Neural ODE, CVAE, Transformer, 1-step Diffusion) on offline mean squared error by 5.9 to 29 percent. On the LIBERO-10 closed-loop benchmark, phase conditioning on Ghost's basin-structured latent yields a 13.5 percentage-point success-rate gain over a feed-forward MLP baseline, and persistent-latent ensembling reaches a 95.7 percent final success rate.

Related papers

• FlowTSFM: Turning Encoder Depth into Quantile Transport [29.781238027602466]
  We introduce FlowTSFM, an encoder architecture that interprets depth as a recurrent transport process.<n>With only 38.8M parameters, FlowTSFM achieves competitive performance on GIFT-Eval and TIME.<n>We also introduce CosMean, a scale-free diagnostic measuring whether recurrent updates consistently align toward the final prediction.
  arXiv  Detail & Related papers  (2026-09-12T01:29:17Z)
• RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers [8.085475675888045]
  RecurrentGPT is a recurrent depth transformer where fixed-depth prelude and coda blocks bracket a single shared core iterated R times.<n>Inspired by gated recurrent neural networks, we employ a lightweight projection and an elementwise update gate to modulate the recurrent update.<n>Our results demonstrate that adaptive depth reuse is a principled strategy for trading parameters for quality.
  arXiv  Detail & Related papers  (2026-08-15T06:22:00Z)
• Spectrally Regularized Latent Flow Matching for Turbulence Generation [0.0]
  We introduce a latent flow matching framework with a spectrally regularized compression stage.<n>On a 2562 DNS dataset at Re_f approx 2250, replacing an MSE-trained VAE with a zone-weighted log-spectral objective raises deep-dissipation retained spectral power.<n>The improved latent representation also yields a substantially better sampling cost-fidelity tradeoff.
  arXiv  Detail & Related papers  (2026-06-10T06:09:51Z)
• How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap [0.0]
  Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model capacity as the experimental variable.<n>We address both gaps by fixing architecture, loss, data split, and training recipe while sweeping only channel width from 1.05K to 40.26K parameters in a minimal depthwiseseparable convolutional U-Net.
  arXiv  Detail & Related papers  (2026-06-07T12:17:25Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• DriftingMol: Decoder-Coupled Drift for One-Pass Property-Conditional Molecular Generation [8.59642525668345]
  We introduce DriftingMol, a two-stage framework that adapts drifting models to a SELFIES latent molecular space.<n>In decoder-coupled drift, drift gradients are backpropagated through the decoder feature map to a DiT generator, inducing a pullback metric.<n>Across 15 controlled variants, models that preserve the gradient path through decoder features achieve higher correlations than the tested latent-space, random-feature, and external-feature drift variants.
  arXiv  Detail & Related papers  (2026-05-24T03:17:20Z)
• N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation [68.47358899451255]
  N-vium is a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware.<n>N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits.
  arXiv  Detail & Related papers  (2026-05-13T08:46:17Z)
• Coupling Models for One-Step Discrete Generation [50.37847093567075]
  Coupling Models is a one-step discrete generative model that learns a direct coupling between discrete sequences and Gaussian latents.<n>It avoids complex continuous flows over the simplex and hand-specified data-to-noise couplings.<n>It reduces LM1B text-generation perplexity by 33% at its lowest-perplexity operating point.
  arXiv  Detail & Related papers  (2026-05-08T03:40:39Z)
• Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression [7.913101398893967]
  We propose a reconstruction-based criterion that measures functional redundancy at the level of individual output channels.<n>We transform a complex interaction field to the frequency domain and train a low-capacity autoencoder to reconstruct normalized spectra.<n>We find that spectral reconstruction fidelity of complex interaction fields is an effective proxy for channel-level redundancy under aggressive compression.
  arXiv  Detail & Related papers  (2026-01-14T10:34:18Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• DeepNet: Scaling Transformers to 1,000 Layers [106.33669415337135]
  We introduce a new normalization function (DeepNorm) to modify the residual connection in Transformer. In-depth theoretical analysis shows that model updates can be bounded in a stable way. We successfully scale Transformers up to 1,000 layers without difficulty, which is one order of magnitude deeper than previous deep Transformers.
  arXiv  Detail & Related papers  (2022-03-01T15:36:38Z)
• End-to-End Multi-speaker Speech Recognition with Transformer [88.22355110349933]
  We replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. We also modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation.
  arXiv  Detail & Related papers  (2020-02-10T16:29:26Z)

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.