Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning Enhancement

• URL: http://arxiv.org/abs/2602.19169v1
• Date: Tue, 02 Dec 2025 16:54:22 GMT
• Title: Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning Enhancement
• Authors: Saba Kublashvili,
• Abstract summary: I introduce Virtual Sharpening (VPS), an inference-time technique that augments frozen transformer linear layers with dynamic, activation-conditioned low-rank perturbations.<n>We present the complete algorithmic framework, analyze its mathematical foundations, and discuss the mechanisms by which activation-conditioned computation may enhance reasoning capabilities in large language models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: I introduce Virtual Parameter Sharpening (VPS), an inference-time technique that augments frozen transformer linear layers with dynamic, activation-conditioned low-rank perturbations. Unlike parameter-efficient fine-tuning methods such as LoRA, which learn static low-rank adapters, VPS constructs its perturbation factors on the fly from batch activation statistics and optional gradient signals, enabling test-time adaptation without persistent parameter updates. The perturbation takes the form Delta W = gamma * W^T V U^T W, where selector matrices U and V are constructed via sparse activation-guided selection or Sylvester-coupled regression. We provide a theoretical analysis of the perturbation's spectral properties and describe an adaptive policy system that modulates perturbation magnitude based on activation energy and token-level entropy. This system incorporates multi-objective verification with iterative refinement for tasks with ground-truth supervision. We present the complete algorithmic framework, analyze its mathematical foundations, and discuss the mechanisms by which activation-conditioned computation may enhance reasoning capabilities in large language models. Implementation and experimental code are available at https://github.com/Saba-Kublashvili/vps-virtual-parameter-synthesis .

Related papers

• ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations [54.886931928255564]
  Low-rank adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning method in deep transfer learning.<n>We propose a novel continuous-time optimization dynamic for LoRA factor matrices in the form of an ordinary differential equation (ODE)<n>We show that ODELoRA achieves stable feature learning, a property that is crucial for training deep neural networks at different scales of problem dimensionality.
  arXiv  Detail & Related papers  (2026-02-07T10:19:36Z)
• Towards Arbitrary Motion Completing via Hierarchical Continuous Representation [64.6525112550758]
  We propose a novel parametric activation-induced hierarchical implicit representation framework, called NAME, based on Implicit Representations (INRs)<n>Our method introduces a hierarchical temporal encoding mechanism that extracts features from motion sequences at multiple temporal scales, enabling effective capture of intricate temporal patterns.
  arXiv  Detail & Related papers  (2025-12-24T14:07:04Z)
• GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning [51.79350934271497]
  GateRA is a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates.<n>By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation.<n> Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods.
  arXiv  Detail & Related papers  (2025-11-15T17:55:47Z)
• Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services [10.421371572062595]
  This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception.<n>The proposed method outperforms mainstream baseline models in key metrics, including precision, recall, AUC, and F1-score.
  arXiv  Detail & Related papers  (2025-08-20T07:52:36Z)
• Graded Transformers [0.0]
  We introduce the Graded Transformer framework, a new class of sequence models that embed inductive biases through grading on vector spaces.<n>The framework enables adaptive feature prioritization, overcoming limitations of fixed grades in earlier models.<n>The Graded Transformer provides a mathematically principled approach to hierarchical learning and neuro-symbolic reasoning.
  arXiv  Detail & Related papers  (2025-07-27T02:34:08Z)
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios [54.58186816693791]
  environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption.<n>We propose a new mechanism, converting the fine-tuning process to a specific- parameter generation.<n>In particular, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components.
  arXiv  Detail & Related papers  (2025-06-30T17:14:12Z)
• Beyond Static Models: Hypernetworks for Adaptive and Generalizable Forecasting in Complex Parametric Dynamical Systems [0.0]
  We introduce the Parametric Hypernetwork for Learning Interpolated Networks (PHLieNet)<n>PHLieNet simultaneously learns a global mapping from the parameter space to a nonlinear embedding and a mapping from the inferred embedding to the weights of a dynamics propagation network.<n>By interpolating in the space of models rather than observations, PHLieNet facilitates smooth transitions across parameterized system behaviors.
  arXiv  Detail & Related papers  (2025-06-24T13:22:49Z)
• Variational quantum simulation of a nonadditive relaxation dynamics in a qubit coupled to a finite-temperature bath [0.0]
  We present an application of the variational quantum simulation framework to capture finite-temperature open-system dynamics on near-term quantum hardware.<n>We modeled the energy exchange with a thermal bath through its Lindblad representation and thereby simulated realistic dissipative effects.
  arXiv  Detail & Related papers  (2025-05-17T14:08:23Z)
• Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions [0.0]
  This work presents a data-driven, non-intrusive framework which combines ROM construction with reduced dynamics identification. The proposed approach leverages autoencoder neural networks with parametric sparse identification of nonlinear dynamics (SINDy) to construct a low-dimensional dynamical model. These aim at tracking the evolution of periodic steady-state responses as functions of system parameters, avoiding the computation of the transient phase, and allowing to detect instabilities and bifurcations.
  arXiv  Detail & Related papers  (2022-11-13T01:57:18Z)
• Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging [6.512092052306553]
  Examples include M/EEG inverse problems, encoding neural models for task-based fMRI analyses, and temperature monitoring schemes. We devise a novel hierarchical flexible Bayesian framework within which the intrinsic-temporal dynamics of model parameters and noise are modeled.
  arXiv  Detail & Related papers  (2021-11-02T15:50:01Z)
• Robust Value Iteration for Continuous Control Tasks [99.00362538261972]
  When transferring a control policy from simulation to a physical system, the policy needs to be robust to variations in the dynamics to perform well. We present Robust Fitted Value Iteration, which uses dynamic programming to compute the optimal value function on the compact state domain. We show that robust value is more robust compared to deep reinforcement learning algorithm and the non-robust version of the algorithm.
  arXiv  Detail & Related papers  (2021-05-25T19:48:35Z)
• Spectral Tensor Train Parameterization of Deep Learning Layers [136.4761580842396]
  We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. We show the effects of neural network compression in the classification setting and both compression and improved stability training in the generative adversarial training setting.
  arXiv  Detail & Related papers  (2021-03-07T00:15:44Z)

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.