Elastic Spectral State Space Models for Budgeted Inference

• URL: http://arxiv.org/abs/2601.22488v1
• Date: Fri, 30 Jan 2026 02:58:19 GMT
• Title: Elastic Spectral State Space Models for Budgeted Inference
• Authors: Dachuan Song, Xuan Wang,
• Abstract summary: Foundation models are typically trained at a fixed computational capacity, while real-world applications require deployment across platforms with different resource constraints.<n>We propose Elastic Spectral State Space Models (ES-SSM), which require only one-time training at full capacity, but can be directly truncated into arbitrary scales for budgeted, runtime inference without retraining.<n>We demonstrate that a single ES-SSM model trained once can be truncated to provide competitive performance compared with modern Transformer and SSM baselines at similar parameter scales.
• Score: 6.579320299248572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models are typically trained at a fixed computational capacity, while real-world applications require deployment across platforms with different resource constraints. Current approaches usually rely on training families of model variants or model distillation, which requires additional training and supports only a pre-selected set of sizes rather than fine-grained adaptation at runtime. In this paper, we propose Elastic Spectral State Space Models (ES-SSM), which require only one-time training at full capacity, but can be directly truncated into arbitrary scales for budgeted, runtime inference without retraining. Our ES-SSM builds on Hankel spectral filtering over a state space model (SSM), coupled with a lightweight input-adaptive gate trained under randomized spectral budgets. Using a shared masked normalization rule over the ordered spectral channels, we encourage predictive capability to concentrate in low-index components, while higher-index components act primarily as refinement. We test our algorithm across long-sequence benchmarks spanning text, logic, retrieval, vision, and audio. We demonstrate that a single ES-SSM model trained once can be truncated to provide competitive performance compared with modern Transformer and SSM baselines at similar parameter scales. Furthermore, by testing under various runtime budgets, we observe smooth and stable budget-performance curves over a wide range of truncation levels.

Related papers

• Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps [4.397130429878499]
  Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs.<n>We propose SDM, a principled framework that aligns the numerical solver with the intrinsic properties of the diffusion trajectory.<n>By analyzing the ODE dynamics, we show that efficient low-order solvers suffice in early high-noise stages while higher-order solvers can be progressively deployed to handle the increasing non-linearity of later stages.
  arXiv  Detail & Related papers  (2026-02-13T05:02:07Z)
• Towards a Principled Muon under $μ\mathsf{P}$: Ensuring Spectral Conditions throughout Training [0.0]
  We show how to reliably guarantee the spectral conditions required by $$P for large language model (LLM) training.<n>We develop a variant of Muon, namely Muon++, that satisfies spectral condition throughout the training process.
  arXiv  Detail & Related papers  (2026-01-04T00:04:05Z)
• Elastic ViTs from Pretrained Models without Retraining [74.5386166956142]
  Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes.<n>We introduce SnapViT: Single-shot network approximation for pruned Vision Transformers.<n>Our approach efficiently combines gradient information with cross-network structure correlations, approximated via an evolutionary algorithm.
  arXiv  Detail & Related papers  (2025-10-20T16:15:03Z)
• The Curious Case of In-Training Compression of State Space Models [49.819321766705514]
  State Space Models (SSMs) tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference.<n>Key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden.<n>Our approach, textscCompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models.
  arXiv  Detail & Related papers  (2025-10-03T09:02:33Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers [57.441926088870325]
  Deep Image Prior (DIP) is a technique that optimized the weights of a randomly-d convolutional neural network to fit a signal from noisy or under-determined measurements. Relative to publicly available implementations of Vector Fitting (VF), our method shows superior performance on nearly all test examples.
  arXiv  Detail & Related papers  (2023-06-06T20:28:37Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)

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.