Neural Network Pruning

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 83% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 161

Jun 16, 2026cs.LG

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression

Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead. Prior compression methods mainly operate at the expert level, either removing entire experts or ranking experts by coarse-grained importance scores. However, such expert-wise decisions are often too coarse to capture fine-grained redundancy, leading to misallocated pruning budgets and limited compression. To address this problem, we observe that information within MoE experts is highly concentrated in a small subset of channels, leaving substantial redundancy even in experts deemed important. Based on this observation, we propose a structural pruning framework tailored for MoE models. Our method reformulates prune-ratio allocation as a channel-score coverage maximization problem and solves it efficiently using an attribution-based approximation. Experiments on DeepSeek and Qwen MoE models show that our method preserves model accuracy under 50% or 25% structured pruning when combined with 4-bit quantization. On Qwen3-30B-A3B, our approach reduces memory footprint by 5.27

\times

and consistently outperforms state-of-the-art baselines across diverse benchmarks.

Yifu Ding, Jiacheng Wang, Ge Yang +4

State Key Laboratory of Complex & Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University · Nanyang Technological University +1

Mixture-of-Experts Pruning LLM Pruning Structured Pruning Mixture-of-Experts Models Neural Network Pruning

Jun 13, 2026cs.CV

DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction

Spatio-temporal prediction supports radar/satellite nowcasting and city-scale traffic monitoring, but modern models are often too expensive for real-time deployment. This stems from a mismatch between dense computation and strong input-dependent redundancy (e.g., calm seas or clear skies). To enable automated, resource-aware architecture optimization in scalable media analysis, we propose Dyna-Pruner, an end-to-end framework for input-dependent co-pruning of data and model structure. A shared-importance synchronization mechanism generates coupled masks that prune redundant regions and their corresponding computational units (e.g., convolutional filters), yielding per-sample sparse sub-networks at inference time. Experiments on WeatherBench, SEVIR, and TaxiBJ show seamless integration with CNN, RNN, and Transformer backbones, reducing FLOPs by up to

70\%

and achieving a

2.5\times

speedup on NVIDIA Jetson AGX Orin with negligible accuracy loss (

<1\%

).

Fuyan Zhang, Yuqi Li, Qing Xu +2

University of Edinburgh · The City College of New York, City University of New York · Institute of Computing Technology, Chinese Academy of Sciences +1

Efficient Neural Network Inference Spatiotemporal Forecasting Neural Network Pruning

Jun 13, 2026cs.CL

Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective

The considerable layer-wise redundancy in large language models (LLMs) has established non-uniform sparsity allocation across layers as the standard pruning approach for efficient compression. Existing layer-wise allocation methods that estimate allocation strategy from local signals such as activation outliers or weight spectra mainly derive from local layer importance, whereas the final post-pruning performance is also influenced by the network's subsequent compensatory capacity. In this paper, we directly characterize this property through controlled perturbation experiments. We make the following empirical findings. First, layers exhibit highly heterogeneous responses to pruning-scale perturbations. In most cases, early layers amplify perturbations, while middle and late layers actively absorb them, with relative L2 drift decreasing monotonically across depth and direction realigning toward the unperturbed hidden-state trajectory. Second, absorption is a large-perturbation phenomenon. Under small perturbations the network exhibits amplification across all layers, and the transition to absorption occurs smoothly as perturbation magnitude grows to pruning scale. This enriches the linearized accumulation theory underlying related works. Building on these findings, we define an absorption coefficient per layer and propose absorption-aware correction, an orthogonal augmentation that improves OWL and AlphaPruning by reducing perplexity by 7.13% and boosting zero-shot accuracy by 1.02% across multiple model families at 70% sparsity.

Tao Jing, Ningxin Wu, Chen Kang +3

LLM Pruning LLM Compression Neural Network Pruning

Jun 12, 2026cs.LG

Squeeze-Release: Iterative Pruning with Exact Structural Minimization

Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We present an exact structural rewrite, which we call minimization, that converts a masked network into a smaller dense network with the same forward function up to floating-point rounding. The Squeeze-Release cycle iterates pruning and minimization with an intermediate release step that re-enables the exact-zero positions inside the compacted tensors as small calibrated noise, turning otherwise wasted capacity back into trainable parameters. Successive cycles use that capacity to find structural redundancy a single pass cannot reach. We additionally introduce CompensatedLayerNorm, a function-preserving replacement for LayerNorm that extends minimization to channel reduction across LayerNorm-equipped residual streams. Squeeze-Release compresses the deployable network to 39x smaller than the unpruned model on a fully-connected model network and 14.8x smaller on modern CNN (ConvNeXt-Tiny), at comparable accuracy. In addition we prove that the rewrite can be extended to transformer architectures.

Roman Denkin, Ida Akerholm, Prashant Singh +1

Department of Information Technology, Uppsala University, Uppsala, Sweden · Science for Life Laboratory, Uppsala University, Uppsala, Sweden

Structured Pruning Neural Network Compression Neural Network Pruning

Jun 12, 2026cs.SD

Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantization

Streaming speaker diarization is crucial for time-critical medical dispatch, but deploying it on resource-constrained hardware requires smaller, faster models. Using SIMSAMU, a dataset of simulated medical-dispatch conversations, we evaluate streaming behavior before compressing the segmentation model with pruning and low-bit quantization. We characterize performance across a range of streaming latency budgets and find that additional buffering is not consistently beneficial, while very low-latency operating points can substantially degrade performance. Our study shows that model compression trades performance for memory footprint, and we highlight an operating point where FP16 reduces model size by half with essentially unchanged real-time factor, at a cost of a 40% relative DER increase against the baseline. This work characterizes the trade-offs for real-time deployment and contributes to speech technology that can enable reliable human communication in time-critical contexts.

Rishit Chatterjee, Tahiya Chowdhury

Department of Computer Science, Colby College, Waterville, Maine, United States

Model Compression Speaker Diarization Low-Bit Quantization Neural Network Pruning

Jun 10, 2026cs.CV

Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning

Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense networks when trained from suitable initializations, its iterative pruning procedure requires multiple complete training cycles. This work evaluates progressive magnitude-based pruning as a single-cycle alternative. The method gradually increases sparsity during training using a linear schedule and updates pruning masks based on active weight magnitudes. We conduct systematic experiments on CIFAR-10 and MNIST across ResNet, VGG-style, and LeNet architectures, comparing the proposed method with representative iterative and initialization-based pruning baselines, including LTH, SNIP, and GraSP. On CIFAR-10, the method achieves 95.12% accuracy on ResNet-18 at 72.9% sparsity, compared with 90.5% reported for LTH. At extreme sparsity, it achieves 93.13% accuracy on a VGG-like architecture at 97% sparsity, compared with approximately 92.0% for SNIP, and 93.44% accuracy on VGG-19 at 97.97% sparsity, compared with 92.19% for GraSP at 98% sparsity. A sparsity-accuracy analysis on ResNet-18 further shows that accuracy remains within 0.1 percentage points of the dense baseline across 70--85% sparsity. These results indicate that progressive magnitude-based pruning provides an effective single-cycle approach for neural network sparsification under the evaluated settings.

Romana Qureshi, Hafida Benhidour, Said Kerrache +1

Department of Computer Science, King Saud University, Riyadh, Saudi Arabia

Sparse Neural Networks Neural Network Pruning

Jun 10, 2026eess.SP

REACH: Interpretability-Driven Feature Identification and Architecture Compression for Multi-Channel Vehicular Channel Estimation

Multi-channel mixed-SNR training improves out-of-distribution (OOD) generalisation of deep learning channel estimators for IEEE 802.11p vehicular communications, yet the internal mechanism responsible for this remains unexplained. This work presents REACH (Relevance-based Explanation and Architectural Compression for cHannel estimators), a gradient-based interpretability framework that operates at two levels. Input-level attribution identifies a subset of time-frequency features consistently relevant across all evaluated channel conditions, enabling input dimensionality reduction with minimal performance loss. Filter-level attribution reveals a near-universal internal representation, providing a representational account of the observed OOD generalisation. Guided by the resulting filter taxonomy, relevance-guided architecture compression substantially reduces both the number of parameters and the number of floating-point operations (FLOPs) with sub-1 dB normalised mean square error (NMSE) degradation, and OOD generalisation degrades more slowly than within-distribution accuracy under increasing compression.

Simbarashe Aldrin Ngorima, Albert Helberg, Marelie H. Davel

Faculty of Engineering, North-West University, South Africa · Centre for Artificial Intelligence Research, South Africa · National Institute for Theoretical and Computational Sciences, South Africa

Feature Attribution OOD Generalization Channel Estimation V2X Communication Neural Network Pruning

Jun 10, 2026cs.SD

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducted on the LibriSpeech dataset suggest that when operating with pruning sparsity of 50% on HuBERT-large, consistent WER reductions of 27.73%/18.61% absolute (34.37%/21.91% relative) over the magnitude-based pruning were obtained on the test-clean and test-other subsets before fine-tuning and 0.19%/0.79% absolute (3.36%/4.62% relative) after fine-tuning with only 3 epochs. Similar WER reductions of 2.86%/5.02% absolute (59.21%/55.29% relative) were observed against magnitudebased pruning on Whisper-large-v3 at 10% sparsity, all with no significant WER increase relative to the uncompressed baseline.

Haoning Xu, Zhaoqing Li, Huimeng Wang +4

The Chinese University of Hong Kong, Hong Kong SAR, China · National Research Council Canada, Canada

Speech Foundation Models Clustering Speech Processing Neural Network Compression Neural Network Pruning

Jun 9, 2026cs.LG

SpenseGPT: Practical One-shot Pruning Enabling Sparse and Dense GEMMs for LLM Inference

Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoretical speedup. However, its strict 50% sparsity constraint often causes non-negligible accuracy degradation under post-training pruning. Meanwhile, existing relaxed sparsity formats either require specialized compiler support or introduce runtime overheads that limit end-to-end speedup. We propose Spense, a practical hybrid sparse-dense format that splits each weight matrix into a 2:4 sparse region and a dense region. This design relaxes the effective sparsity constraint while remaining compatible with existing high-performance sparse and dense GEMM libraries, avoiding both custom compiler support and input activation expansion. Building on this format, we introduce SpenseGPT, a one-shot post-training pruning method that produces sparse and dense regions. Notably, we show that selecting the right dense regions is important, and we devise two different strategies to choose them. Experiments on Qwen3-32B and Seed-OSS-36B demonstrate that our method achieves up to 1.2x end-to-end decoding speedup on B200 GPUs with FP8 precision, while preserving accuracy. To the best of our knowledge, this is the first one-shot pruning demonstration of real-world end-to-end LLM decoding speedup from semi-structured sparse tensor cores on recent GPUs such as B200s, while maintaining model quality.

Jaeseong Lee, Seung-won Hwang, Samyam Rajbhandari

Snowflake AI Research* · Seoul National University†

LLM Pruning High-Performance Computing Structured Sparsity LLM Inference Acceleration Neural Network Pruning

Jun 4, 2026cs.LG

Less is MoE: Trimming Experts in Domain-Specialist Language Models

Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment challenges. Prior MoE compression approaches catastrophically fail when evaluated on general-purpose benchmarks beyond commonsense reasoning. We trace this failure to the granularity of compression: important capabilities are distributed across experts but concentrated in FFN sparse intermediate dimensions. To identify these dimensions, we use Fisher importance which outperforms activation-, router-score-, and magnitude-based alternatives, and identifies tiny sets of task-critical dimensions: in Qwen1.5-MoE, removing as few as 12 of 1.35M routed-FFN intermediate dimensions collapses GSM8K accuracy while largely preserving factual-knowledge performance. Building on this, we propose Fisher-MoE, which operates within FFN to remove intermediate dimensions ranked by Fisher importance. At the same 50% MoE compression ratio, Fisher-MoE preserves model capability, while reducing weight memory by ~45% and improving inference throughput by 21%. These findings suggest intermediate dimension granularity is an effective unit for both compression and ranking where capability concentrates in MoE models.

Haoze He, Xinkai Zou, Xuan Jiang +4

Carnegie Mellon University · UCSD · MIT

Mixture-of-Experts Pruning LLM Pruning LLM Inference Acceleration Structured Pruning Mixture-of-Experts Models Neural Network Pruning

Jun 3, 2026stat.ML

Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks

The deep neural network is a widely used framework in machine learning that has been widely applied in various fields. However, deep neural networks often involve a large number of parameters and inputs, many of which may be irrelevant to the goal or true output. These parameters and input variables not only increase computational complexity, but also contribute to additional computational cost. One solution to this problem is knockoff methods, which have proven successful in controlling false discovery rates in high-dimensional regression. Building on the knockoff methods and using the regularised neural network, this paper proposes three variable screening methods under the condition of controlling false discovery rates: one layer filter, multiple layers filter, and variable weight aggregation filter. In comparison with existing algorithms, we find that our algorithms show satisfactory performance.

Wenyu Liao, Yiqing Shi, Fang Xie

Guangdong Provincial Key Laboratory of IRADS, Beijing Normal-Hong Kong Baptist University, Zhuhai 519087, China

FDR Control Feature Selection Neural Network Pruning

Jun 2, 2026cs.NE

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers

The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-of-the-art works compress SViT models through unstructured pruning, which needs specialized hardware accelerators for their specific sparsity patterns to maximize efficiency gains. Moreover, their manual approach requires a huge design time to find an appropriate pruning setting for each network, thus making this approach not scalable. To address this limitation, we propose PrimeSVT, a novel framework that performs automated memory-aware structured pruning on pre-trained SViT models, thereby maximizing their efficiency gains during inference amenable to widely-used computing architectures. To achieve this, PrimeSVT first sorts the SViT layers based on their sizes (i.e., number of parameters), identifies the targeted pruning layers based on their robustness under different pruning rates, then leverages this order for compressing the model layer-by-layer sequentially from the largest one to the smallest one (i.e., so-called prioritized compression policy), while considering the user-defined constraints (i.e., acceptable accuracy and memory saving). In each layer, PrimeSVT employs channel-wise filter pruning based on their L2-norm values to structurally remove the non-significant weights. Experimental results show that PrimeSVT saves 26.68% memory through automated single-shot pruning, while preserving accuracy within 3% (70.3% without fine-tuning and 72.9% with fine-tuning) from the original unpruned SViT model (73.3%), thus meeting the accuracy and memory constraints. These show that our PrimeSVT framework enables design automation for SViTs and their embedded implementation.

Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio +1

eBRAIN Lab, Division of Engineering, New York University (NYU) Abu Dhabi, United Arab Emirates (UAE)

Memory-Efficient Inference Spiking Neural Networks Neural Network Compression Neural Network Pruning

Jun 2, 2026cs.NE

PSViT: A Methodology for Structurally Pruning Spiking Vision Transformers

Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However, their large sizes limit their deployments for resource-constrained embedded platforms, underscoring the needs of model compression. One of prominent compression techniques is pruning, and the state-of-the-art works employ unstructured pruning techniques to compress SViT models. Such techniques require specialized hardware architectures tailored for the sparsity patterns to maximize their efficiency benefits, making this approach not scalable. To address this, we propose PSViT, a novel methodology to perform structured pruning on SViT models, hence making it possible to efficiently accelerate their inference using the existing and widely-used computing architectures. To do this, PSViT employs several key steps: uniform channel-wise filter pruning to structurally eliminate the non-significant weights, sensitivity analysis to evaluate the impact of channel-wise pruning of individual layer on accuracy and network size, as well as fine-grained channel-wise pruning based on the sensitivity analysis and the given network architecture. Experimental results show that PSViT effectively obtains 22.4% memory saving through single-shot pruning, while maintaining high accuracy within 3% (70.3% without fine-tuning and 72.8% with fine-tuning) from the original non-pruned SViT model (73.3%) on the ImageNet-1K. These results also show that the PSViT methodology advances the effort in enabling efficient SViT deployments on resource-constrained applications.

Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio +1

eBRAIN Lab, Division of Engineering, New York University (NYU) Abu Dhabi, United Arab Emirates (UAE)

Efficient ViTs Spiking Neural Networks Structured Pruning Neural Network Pruning

Jun 1, 2026cs.CV

VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning

3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic importance scores or synchronous batch updates, leading to suboptimal compression and training instability. We propose VEDAL, a principled framework that formulates Gaussian pruning as variational free energy minimization. Our approach introduces (1) a prediction-error gating mechanism that asynchronously activates pruning based on per-Gaussian reconstruction uncertainty, and (2) a variational uncertainty head that models pruning decisions as latent variables with learnable priors. The free energy objective naturally balances reconstruction fidelity against model complexity through an information-theoretic lens. Extensive experiments on Mip-NeRF 360, Tanks&Temples, and Deep Blending demonstrate that VEDAL achieves 5.2x compression with only 0.31 dB PSNR drop, outperforming PUP 3D-GS by +0.05 dB at a higher compression ratio and LightGaussian by +0.35 dB at comparable quality, while maintaining real-time rendering at 185 FPS.

Aoduo Li, Jiancheng Li, Huan Ye +5

Guangdong University of Technology · Huizhou Boluo Power Supply Bureau, Guangdong Power Grid Co., Ltd. · Shenzhen Polytechnic University +1

3DGS Compression 3D Gaussian Splatting 3D Gaussian Pruning Variational Inference Neural Network Pruning

Jun 1, 2026cs.CL

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference

Small Language Models (SLMs) offer a balance between capability and computational feasibility. Neural scaling laws inform their optimal training, suggesting that they possess rich internal representations that scale with their size. However, deploying even these SLMs can be challenging under strict resource constraints. Language model probing provides methods for analyzing the linguistic knowledge encoded in a model's internals. We propose ProbScale, a framework that unifies insights from scaling laws and probing to identify parameter-efficient subnetworks within pre-trained SLMs. ProbScale utilizes the high-quality representations of well-scaled SLMs and uses task-specific probes to mathematically quantify the relevance of each layer for target downstream capabilities. This allows selecting subnetworks that optimally trade off performance against parameter size. We formulate the subnetwork selection as finding a layer subset maximizing aggregated, task-weighted probe performance under a parameter budget. Experiments on representative SLMs such as RoBERTa-Large and T5-Base demonstrate that ProbScale identifies subnetworks achieving significant parameter reduction, from 5 to 10 times, while maintaining high performance (95% to 98% of the original SLMs) on targeted tasks, outperforming heuristic baselines.

Sourav Das

Department of Computer Science and Engineering Indian Institution of Information Technology Kalyani Kalyani, West Bengal, India

Small Language Models Efficient Language Model Inference Neural Network Pruning

Jun 1, 2026cs.LG

CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search

Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training. Among existing methods, RIA introduces relative importance scores normalized by row and column sums, achieving state-of-the-art accuracy. However, RIA considers only 1D cross-shaped (row/column) directional information and assigns equal weight to row and column contributions. In this paper, we propose \textbf{CRePE}, which incorporates 2D local neighborhood context and adaptive coefficients into Relative Importance scoring. CRePE consistently outperforms existing PTP methods across diverse models and sparsity settings. However, identifying optimal adaptive coefficients via perplexity (PPL)-based hill climbing requires numerous PPL evaluations and approximately 11 hours of search time. To address this, we propose \textbf{PHO} (Proxy-based Hyperparameter Optimization), which eliminates the need for repeated PPL measurements and reduces the search time to approximately 20 minutes. Furthermore, the optimal hyperparameter configuration found by PHO on one model transfers well to other models, demonstrating strong generalization. Finally, we verify that CRePE can be orthogonally combined with existing techniques including Channel Permutation, non-uniform sparsity allocation, and re-pruning methods.

Cheonjun Park

Hankuk University of Foreign Studies

LLM Pruning LLM Compression Hyperparameter Optimization Neural Network Pruning

May 31, 2026cs.LG

STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing

Pruning is a process designed to reduce the number of weights in a large neural network. This can substantially speed up inference but might cause a considerable reduction in the model's accuracy, and thus it is usually followed by a healing process that regains some of the lost accuracy. In this paper, we propose a new healing method, STARFISH, that can recover (most of) the accuracy of any pruned network efficiently. The main idea of STARFISH is to optimize the pruned network to align with the original network's internal state representations using a tiny calibration set of unlabeled examples. For the common case of removing 50% of the weights, STARFISH healing improves the recovered accuracy by up to 22% over the state-of-the-art methods on ViT-based networks. Its advantage is even more pronounced under aggressive pruning. For example, after eliminating 75% of the weights in a DeiT-B network for ImageNet, STARFISH uses only 0.4% of the number of training images as a calibration set and recovers 82% of the original dense accuracy, whereas competing recovery techniques reach only 40% of the dense model accuracy.

Shir Maon, Odelia Melamed, Adi Shamir

Weizmann Institute of Science

Neural Network Compression Neural Network Pruning

May 29, 2026cs.LG

Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits

Deep neural networks often contain redundant hidden units. Removing individual weights can reduce parameter count, but unstructured sparsity is not always easy to exploit in standard dense implementations. This paper develops a structured pruning framework in which complete neurons are removed using multi-armed bandit (MAB) algorithms. Each candidate neuron is treated as an arm; pulling an arm temporarily masks that neuron, measures the change in loss on a sampled mini-batch, restores the neuron, and updates an estimate of its safe-removal reward. The framework supports stochastic policies, including Epsilon-Greedy, Softmax, UCB1 and Thompson Sampling, and multiplicative-weight policies, including Hedge-style multiplicative weights and EXP3. We evaluate the method on tabular classification, tabular regression and deep neural-network benchmarks covering image, text and reasoning tasks. Statistical comparisons using the Friedman test followed by the Nemenyi post-hoc test show significant differences between methods. On tabular classification tasks, UCB1 obtains the highest mean rank among pruning policies and improves on the unpruned neural network. On regression tasks, UCB1 obtains the highest mean rank and is statistically competitive with, or superior to, several standard regression models according to R^2. On deep-learning tasks, UCB1 and Thompson Sampling obtain the strongest ranks, and several MAB policies significantly outperform the unpruned model, magnitude-based neuron pruning and greedy activation-variation pruning. The results show that MAB-based neuron pruning is an effective and computationally practical approach for structured model reduction.

Salem Ameen, Sunil Vadera

School of Science, Engineering and Environment, University of Salford, Salford, United Kingdom

Multi-Armed Bandits Neural Network Compression Neural Network Pruning

May 27, 2026cs.CL

PrunePath: Towards Highly Structured Sparse Language Models

Feed-forward networks (FFNs) dominate the parameter count and computation of modern language models, yet existing pruning methods often struggle to convert sparsity into hardware-friendly inference efficiency gains. We introduce \textbf{PrunePath}, a budget-adaptive structured sparsification framework for FFN layers. Built on MoEfication, PrunePath replaces independent expert-wise thresholding with a softmax-normalized routing distribution and activates important experts under a cumulative-mass threshold. This formulation imposes a token-level probability budget, enabling adaptive expert counts and a direct inference-time sparsity knob from a single checkpoint. Across NLU, NLG, and instruction-tuning evaluations, PrunePath achieves a favorable sparsity--performance trade-off compared with existing static pruning and MoEfication-based methods. We further implement Triton kernels for KV-cache decoding to translate the resulting structured sparsity into practical memory savings and measurable decoding-speed improvements. These results demonstrate the superior performance of PrunePath for building highly sparse, deployment-friendly large language models.

Zhexuan Gu, Zixun Fu, Yancheng Yuan

Department of Applied Mathematics, The Hong Kong Polytechnic University

Mixture-of-Experts Pruning LLM Pruning Mixture-of-Experts Language Models Structured Sparsity Structured Pruning Sparse Neural Networks+2

May 26, 2026cs.CV

PARE: Pruning and Adaptive Routing for Efficient Video Generation

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but typically commit to a fixed architecture that cannot adapt to individual inputs or denoising stages. We propose PARE (Pruning and Adaptive Routing for Efficient video generation), which jointly compresses width and depth with structure-aware pruning and input-adaptive routing. For width, we observe that attention heads specialize into spatial and temporal roles, and design importance scoring that accounts for this distinction to prevent motion-critical temporal heads from being pruned prematurely. For depth, we train a lightweight router conditioned on denoising timestep and visual content to dynamically select which blocks to execute at each step, enabling per-input compute adaptation rather than static block removal. A progressive pipeline first recovers width-pruned quality via distillation, then jointly optimizes the student and router to decouple the two learning objectives. Experiments on Wan2.1-14B for both image-to-video and text-to-video generation show that PARE substantially reduces per-step computation while preserving quality across VBench dimensions, and composes with step distillation for further acceleration.

Yutong Wang, Yunke Wang, Tianfan Xue +4

The University of Sydney · The Chinese University of Hong Kong · Shanghai AI Laboratory

Video Diffusion Models Diffusion Transformer Diffusion Model Inference Acceleration Diffusion Models Neural Network Pruning

May 26, 2026cs.LG

Resource-Constrained Affect Modelling via Variance Regularisation Pruning

Affective computing systems are increasingly embedded in pervasive and interactive environments, such as adaptive games, assistive technologies, and resource-constrained platforms, where computational efficiency must be balanced with reliability across diverse users. Model pruning offers an effective way to reduce computational demands, yet existing approaches typically optimise for sparsity alone, without accounting for how parameter removal impacts robustness across individuals. In this work, we introduce Variance-Regularised Pruning (VR), a pruning framework that explicitly incorporates cross-participant stability into the sparsification process. Rather than relying solely on average prediction error, VR evaluates each connection based on its joint contribution to both prediction accuracy and variability across users, prioritising parameters that remain reliable under distributional differences. We evaluate the proposed approach on the AGAIN dataset, which includes arousal annotations collected across nine affect-eliciting game environments. Experimental results demonstrate that VR maintains competitive Concordance Correlation Coefficient (CCC) performance even at 80% sparsity without additional fine-tuning, highlighting its suitability for deployment in real-world, resource-limited affect-aware systems. Overall, the proposed framework supports the development of compact, robust affective models that can operate reliably in real-world interactive environments.

Kosmas Pinitas, Konstantinos Katsifis

Mediterranean College, Athens, Greece · University of Derby, Derby, UK

Cost-Aware Inference Affective Computing Neural Network Pruning

May 25, 2026cs.AI

MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. Structured pruning offers a natural solution; however, existing methods fail to preserve CoT reasoning accuracy in VLMs. We identify two key reasons: (1) CoT consistency depends on sparse transition points (pivot tokens) in the generation trajectory, while existing pruning methods are CoT-agnostic; and (2) pruning methods designed for unimodal LLMs do not account for activation-distribution differences across visual and textual modalities. Motivated by these observations, we propose MuCRASP, a structured pruning framework that targets reasoning-critical components while preserving cross-modal alignment and accounting for layer-wise sensitivity under a global parameter budget. Experiments on four VLMs across three reasoning benchmarks show that MuCRASP consistently preserves reasoning quality under increasing compression. At 30% pruning on Qwen2.5-VL-7B, MuCRASP achieves an LLM-as-a-Judge score of 8.87 versus 7.32 for the strongest baseline on physical reasoning tasks. Furthermore, MuCRASP maintains high reasoning consistency up to 50% pruning, significantly outperforming prior pruning approaches while exhibiting lower perplexity degradation.

Aritra Dutta, Somak Aditya

Indian Institute of Technology, Kharagpur

Vision-Language Models Efficient VLM Inference Multimodal CoT Reasoning Structured Pruning Neural Network Pruning

May 25, 2026cs.LG

Towards the Connection between Activation Sparsity and Flat Minima

The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computation costs without sacrificing performance. To theoretically explain this phenomenon, existing works have shown that activation sparsity does not result from the data properties or data fitting but from the implicit bias of the training process. However, these connections are obtained with strong assumptions, which cannot be applied to deep models standardly trained with a large number of steps. Different from these works, we find that the flatness of loss landscapes is also closely related to the MLP activation sparsity and can serve as a weaker and naturally emerging assumption standard deep networks. Specifically, we find that 1) the MLP activation sparsity equals a ratio between "augmented flatness" (a weighted sum of flatness measures) and the product of the input norm and activation gradient of the MLP. We empirically find that this ratio decreases during training, leading to sparse activations. 2) We also propose the notion of derivative sparsity, which reduces to activation sparsity under ReLU, but further enables pruning in the backward propagation and is more stable than activation sparsity. With the theoretical findings, we can further encourage activation sparsity by decreasing the numerator and increasing the denominator of the ratio using three methods. These plug-and-play modifications can effectively reduce the ratio and produce sparser activations. Experiments on ImageNet-1K and C4 demonstrate relative improvements of at least 36% on inference sparsity and at least 50% on training sparsity over vanilla Transformers, indicating further potential cost reduction in both inference and training

Ze Peng, Jian Zhang, Lei Qi +2

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · Institute of Brain-Machine Interface, Nanjing University, Nanjing 210023, China · School of Computer Science and Engineering, Southeast University, Nanjing 211189, China

Efficient Neural Network Inference Activation Sparsity Flat Minima Neural Network Training Dynamics Neural Network Pruning

May 25, 2026cs.LG

Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation

At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed across the network, and whether that damage can be recovered by a fixed lightweight repair procedure. We study this problem through the lens of repair conditioned sparsity allocation. We introduce Relative Repairability (RR), a calibration based diagnostic that compares the raw activation distortion caused by layerwise pruning with the residual distortion left after channelwise variance matching repair. RR estimates the fraction of local damage that remains after repair, using only unlabeled calibration data. Across ResNet18, ResNet34, and VGG16 BN on CIFAR10 and CIFAR100, we find that RR is not a universally dominant allocation rule. Instead, it is most useful near an architecture dependent recoverability transition, where standard structural or magnitude based allocation priors begin to lose reliability but post repair recovery has not yet fully collapsed. On CIFAR100 ResNet18, a fine grained sweep shows that RR improves over ERK across the central transition band and surpasses LAMP near the upper part of this band. A projection forced ablation further shows that capped ERK can over protect projection layers, shifting excessive sparsity onto regular convolutions and reducing post repair recovery. These results suggest that high sparsity pruning should allocate not only retained weights, but also repairable damage.

Qishi Zhan, Liang He, Minxuan Hu +1

Marquette University · Tongji University · Cornell University +1

Neural Network Compression Neural Network Pruning

May 24, 2026cs.LG

Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation

Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models. Olfactory navigation is a highly dynamic and non-stationary task that benefits from real-time continual learning. We introduce an adaptive framework called Grow-Prune-Freeze (GPF) networks that enable an agent to continually learn through growing, pruning, and freezing early layers of its policy in response to world complexity. Grounding GPFs in non-linear random matrix theory, we show that the work of Pennington & Worth (2017) can be extended from single hidden layers to n-layer continual-learning models, and that eigenvalue composition of network weights is preserved as successive layers are added. We show that GPFs based on Expected SARSA achieve a 94% success rate on turbulent plume navigation - a partially observable, non-stationary task representative of the "big world" challenges that motivate adaptive learning in robotics - and provide supporting methodology for applying GPFs in other world models. Further experiments amount evidence that GPFs may generalize well to other machine learning tasks such as reinforcement learning in Atari, image classification, and autoregressive language models. We open source all code and data to encourage improvements on and more research in olfactory robotics.

Kordel K. France, Ovidiu Daescu

Department of Computer Science, University of Texas at Dallas, USA

Non-Stationary RL Partially Observable RL Robot Navigation Continual Learning Adaptive Learning Neural Network Pruning

May 23, 2026cs.LG

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets. The main practical contribution is accuracy retention under short calibration and fine-tuning schedules, rather than a long post-pruning reoptimization pipeline. The theory gives deterministic data-path certificates: if the removed component

R

has small propagated logit effect

L_s \| R ψ_1(s) \|_\infty

, pruning decreases an elastic-net objective and preserves samples whose dense margin exceeds twice the perturbation. The zero-budget case gives perfect pruning; a prune--restore extension models weight restoration inside a fixed sparse-execution pattern; and an additive

L_2

-regularized model shows admissible random-like components vanish at the training limit, with persistent spikes stabilizing as the MP bulk collapses. Under iid-Gaussian sufficient conditions, the fitted MP edge

σ_+

gives a high-probability layerwise budget signal. On ImageNet-1k, after only three distillation epochs, ViT-B/16

2{:}4{+}

ToMe reaches

83.41\%

top-1 (

-1.70

pp from dense) at

59.81\%

sparse-execution MAC reduction, with

1.388\times

best-observed A40 native-

2{:}4

backend speedup for the same checkpoint and ToMe graph; a separate no-ToMe A100 endpoint gives

2.705\times

. At structured sparsity, ViT-B/16

6{:}12

reaches

83.74\%

, ViT-L/16

8{:}16

dense+permutation reaches

85.33\%

(

-0.51

pp), and ConvNeXtV2-Base

12{:}16

reaches

86.35\%

(

-0.37

pp). For CNNs, ResNet50

8{:}16

dense+permutation reaches

75.87\%

(

-0.26

pp), and ResNet152d CAST-conv+permutation reaches

81.33\%

(

-1.53

pp) at

{\sim}50\%

MAC accounting with a

1.62\times

A40 im2col

+2{:}4

sparse-GEMM audit.

Leonid Berlyand, Theo Bourdais, Houman Owhadi +1

Department of Mathematics Pennsylvania State University University Park, PA 16802, USA · Department of Computing and Mathematical Sciences California Institute of Technology Pasadena, CA 91125, USA

Structured Pruning Sparse Neural Networks Image Classification Neural Network Pruning

May 21, 2026cs.LG

Posterior Collapse as Automatic Spectral Pruning

We show that posterior collapse in

β

-VAEs implements automatic spectral pruning. A latent mode collapses if its contribution to reconstruction is below the cutoff set by

β

. Equilibrium solutions with different

β

thus reveal a cascade of collapses as latent modes decouple from least to most useful. We derive this as a consequence of the loss via a Landau stability analysis. We define a latent-rescaling-invariant order parameter that ranks active latent modes and whose collapse thresholds identify which effective variables to inspect first. In the linear Gaussian case, the collapse spectrum, utility spectrum, and normalized PCA spectrum coincide, and each collapse follows a mean-field law. We test these predictions on the WorldClim dataset.

Johannes Hirn

1Image Processing Laboratory (IPL), Universitat de València, Paterna, València 46980, Spain∗

Variational Autoencoders Posterior Collapse Neural Network Pruning

May 21, 2026cs.LG

Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation

Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less costly, yet also less accurate, aggregate models. We introduce partial fusion of networks, which interpolates between ensembles and weight aggregation and thus allows for a flexible tradeoff between computational cost and performance. A direct way to achieve this is to extend existing weight aggregation methods based on neuron-level similarity between different networks, where partial fusion then only aggregates weights of neurons which are most similar. We showcase one particular method to jointly identify which neurons are most similar and match them via partial optimal transport. Further, we consider the more general perspective of weight aggregation and partial fusion as generalized pruning of ensemble models, where neurons cannot just be deleted, but also linearly combined. Finally, we show that generalized pruning applied to a single network yields similar benefits as partial fusion by allowing for a tradeoff between isolating, deleting, and linearly combining neurons based on similarity. Our code is available at https://github.com/Fabian-Mor/partial_fusion_nn.

Fabian Morelli, Stephan Eckstein

Department of Computer Science, University of Tübingen, Germany · Department of Mathematics, University of Tübingen, Germany.

Inverse Optimal Transport Ensemble Learning Deep Ensembles Model Merging Neural Network Compression Neural Network Pruning

May 21, 2026cs.LG

How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability

Unstructured magnitude pruning at high sparsity can reduce neural network accuracy to near-random performance, while labeled retraining may be unavailable in practical deployment settings. Label-free post-pruning repair methods can partially recover collapsed sparse models, but their effectiveness depends on the sparse model left by the upstream pruning allocation. This paper studies how sparsity allocation shapes post-repair recoverability under a fixed activation-statistic repair backend. We compare ERK and LAMP allocations under the same label-free repair protocol across CIFAR-10, CIFAR-100, and Imagenette with ResNet-18, ResNet-34, and ResNet-50 at sparsities from 90% to 95.5%. The results show that allocation choice can substantially change post-repair accuracy at the same global sparsity, and that the preferred allocation varies with architecture, dataset difficulty, and sparsity level. We identify a repair-sensitive transition regime in which BatchNorm recalibration begins to fail, while activation-statistic repair still recovers nontrivial accuracy. Additional validation on ImageNet-100 and DenseNet-121 shows that the location and width of this recoverable regime depend on data scale and connectivity structure. These findings suggest that pruning allocation and post-pruning repair should be studied jointly, since the allocation determines how much activation signal remains available for label-free recovery.

Qishi Zhan, Minxuan Hu, Liang He

Marquette University · Cornell University · Tongji University

Sparse Recovery Neural Network Pruning

May 20, 2026cs.LG

Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed channels can coexist with channels that retain informative activation variance within the same layer. Existing layer-wise activation repair methods apply a single correction to the whole layer, and can therefore over-amplify damaged channels while trying to restore the layer-level signal. We propose Adaptive Signal Resuscitation (ASR), a training-free channel-wise repair method that matches the granularity of repair to the granularity of damage. ASR estimates a variance-matching correction for each output channel and stabilizes it with a data-driven shrinkage rule, suppressing unreliable corrections for channels with weak post-pruning signal while preserving corrections for healthier channels. Applied before BatchNorm recalibration, ASR requires only forward passes on a small calibration set and no retraining. Across three datasets, four convolutional architectures, and both unstructured and structured sparsity settings, ASR generally improves over layer-wise repair, with the clearest gains in high-sparsity regimes. On ResNet-50 at 90% sparsity, ASR recovers 55.6% top-1 accuracy on CIFAR-10, compared with 41.0% for layer-wise repair and 28.0% for BatchNorm-only recalibration. Ablations show that naive channel-wise variance matching is insufficient, and that shrinkage stabilizes post-pruning repair.

Qishi Zhan, Ziheng Chen, Minxuan Hu

Department of Mathematical and Statistical Sciences, Marquette University, USA · The University of Texas at Austin, USA · Cornell Ann S. Bowers College of Computing and Information Science, Cornell University, USA

Neural Network Compression Neural Network Pruning