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

Jul 19, 2026cs.CV

Searching for Task-Specific Vision Paths: Evolutionary Block Pruning Across Vision-Language Models

Vision-language models normally execute the same complete vision encoder for every question, even when OCR, counting, object, attribute, and spatial queries may not require identical computation. We study whether fixed-budget combinations of vision blocks can be skipped without fine-tuning. A shared K-block route skips one searched set of exactly K blocks for every question, while a capability-specific K-block policy selects one same-size route using a known capability label. We introduce a source-balanced evolutionary search and compare it with independent ranking, contiguous removal, and random routes at matched budgets. Experiments use Qwen2.5-VL-3B-Instruct, SmolVLM2-2.2B-Instruct, and an 876-example image-disjoint selection split. Search transfers across architectures: on SmolVLM2, the searched shared four-block route beats independent construction by 4.91 percentage points. Capability specialization is less stable. On Qwen, the six-block capability policy beats the shared route by 2.17 points, driven by a 7.10-point OCR gain. On sealed IIIT5K, however, the SmolVLM2 OCR-specific route trails its shared route by 13.6 points. Combinatorial search reliably improves route construction, but capability labels do not define universally transferable vision pathways.

Tarun Tomar

Efficient VLM Inference Neural Network Pruning

Jul 18, 2026cs.LG

Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding

The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token. That pool is why these models do not fit on the machines most developers own, yet for a user who only wants coding help, most experts encode abilities that will never be invoked. We ask how many experts can be removed, and which, by pruning two recent open-weight MoE models from different families (Qwen3.6-35B-A3B and Gemma-4-26B-A4B) under five selection strategies, judged the way a user would: by whether the model still writes correct code. Half the experts can be removed from either model with no statistically detectable loss on the primary code benchmark, and the damage lands almost entirely on abilities outside coding, the intended trade. But the winning strategy flips between the two models, so a recipe validated on one family cannot be assumed to work on another. We further show that perplexity, the metric much of the pruning literature leans on, can rate a broken model above an intact one; that a lightweight fine-tune recovers about half of what aggressive pruning loses; and that against quantizing the full model to the same memory, pruning wins only where quantization would have to drop below 3 bits per weight. Five attempts to overturn that crossover, with failure criteria fixed in advance (better calibration, guarded selection, causal expert importance, failure attribution, and an agentic evaluation letting each model repair its failures from execution feedback), all leave it standing; the last shows single-shot benchmarks overstate compression penalties broadly, as one repair turn erases the 2-bit quantization penalty entirely. Expert pruning works, but it demands per-model validation on the task the model will actually serve.

Anik Jha

1Independent Researcher

Mixture-of-Experts Pruning Mixture-of-Experts Language Models Neural Network Pruning

Jul 14, 2026eess.AS

Efficient Text-to-Audio Generation via Pruning

Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their practical deployment is hindered by the substantial computational cost of the U-Net denoising backbone. In this work, we apply model pruning to improve the computational efficiency of AudioLDM, a U-Net-based text-conditioned audio latent diffusion model. We analyse parameter redundancy across U-Net convolutional blocks and evaluate a filter-pruning strategy. Pruning is guided by norm-based criteria and followed by lightweight finetuning to recover performance losses. Experimental results demonstrate that up to 83% of the parameters and 39% of the multiply-accumulate operations of U-Net have been reduced while maintaining, and in some cases improving, generation quality compared to the baseline unpruned network. We find that pruning affects AudioLDM's ability to generate certain sound events including safety-critical sounds such as gunshots, sirens, and explosions, as well as mechanical sounds such as drills and sewing machines, and other sounds such as sprays and tick-tocks, which are mostly recovered by lightweight finetuning of the pruned model.

Arshdeep Singh, Yi Yuan, Yun Chen +2

1King’s College London (KCL) · University of Surrey, UK

Text-to-Audio Generation Latent Diffusion Models Audio Diffusion Models Neural Network Pruning

Jul 13, 2026cs.LG

An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals

Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism. We give an exact instrument for measuring how a trained model uses these modes. Because the state matrix is diagonal, each channel's output decomposes exactly into per-mode contributions, and a per-(layer, channel, window) Gram tensor yields the exact output error of dropping any subset of modes, offline, at any budget. Validated against the reference implementation to a relative error of

2.3\times10^{-7}

on the Mamba-1 family where it is exact, the instrument predicts a layer's deployed pruning error to a median relative deviation of

5\times10^{-7}

over

4{,}464

configurations, its floor set by the reconstruction. Applying the instrument across the Mamba-1 family (130M--2.8B), the deployed 7B Falcon-Mamba, and Mamba-2, we find that trained models re-allocate their state space with the input: which modes carry the signal migrates across contexts, and at the most affected layers a per-input oracle roughly halves the output error of a fixed mode set. Frozen-signal counterfactuals attribute the migration primarily to the input-dependent write map

B_t

; the timestep usually identified with selectivity carries almost none of it. Input-scheduled mode pruning on this measurement outperforms static, Hankel-based, and layer-adaptive rankings at every scale from 130M to the deployed 7B Falcon-Mamba, and at half the state budget it matches the unpruned model. Because the scheduler reads each window's mode usage from a first pass, this demonstrates realizable headroom; we claim no deployed compute or memory saving.

Raktim Bhattacharya

Aerospace Engineering, Texas A&M University

Selective SSMs Neural Network Pruning State Space Models

Jul 13, 2026cs.CV

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning

In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available at https://github.com/ntuliuteam/Teco.

Hao Kong, Di Liu, Xiangzhong Luo +5

School of Computer Science and Engineering, Nanyang Technological University, Singapore · HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University, Singapore · Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway. +1

Efficient Neural Network Inference Convolutional Neural Networks Edge ML Lightweight CNNs Neural Network Pruning

Jul 11, 2026eess.AS

WaveNet-Style Guitar Amplifier Model Pruning for Real-Time iOS Deployment

WaveNet-style convolutional networks emulate tube amplifiers and distortion pedals with high fidelity, but their computational cost has confined them to desktops or dedicated DSP hardware. We present a sparse-enabled WaveNet inference engine for iOS that runs heavily pruned neural guitar amplifier models in real time on iPhones. Aggressive iterative magnitude pruning removes 90% of the network weights with no perceptible loss in quality. A custom sparse C++ engine turns this sparsity directly into compute savings, sustaining low-latency real-time operation on a CPU-only iPhone implementation where the dense model cannot. On-device output matches the trained model to within int16 quantization error. At the demonstration, visitors will play a guitar through the app on iPhone hardware and A/B the on-device pruned model against the physical pedal it emulates. Source code and audio examples are available at https://github.com/ryos17/wavenet-imp.

Ryota Sato, Eli Silverstein

Dept. of Electrical Engineering Stanford University Stanford, USA

Efficient Neural Network Inference On-Device Inference Neural Network Pruning

Jul 8, 2026cs.CL

PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning

One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance. We propose PALS (Percentile-Aware Layerwise Sparsity), which adjusts per-layer sparsity based on the 99th percentile of activation magnitudes, bounded to

\pm 5\%

around the target ratio. On LLaMA-2-7B at 50% sparsity, PALS achieves 10.96 WikiText-2 perplexity versus 12.92 for uniform Wanda (mean over 9 runs,

p < 0.001

). The benefit is architecture-dependent: LLaMA-3-8B shows marginal gains and Mistral-7B shows none. We also find that gradient-based allocation -- the seemingly more principled approach -- produces results worse than random, suggesting that gradient magnitude does not predict the impact of discrete weight removal. PALS adds negligible cost to the pruning pipeline and requires no fine-tuning.

Yazdan Jamshidi, Alexey Shvets

Palo Alto Networks

LLM Pruning LLM Compression Neural Network Pruning

Jul 7, 2026cs.CV

Hardware-aware Graph Neural Networks prunning for embedded event-based vision

Event-based cameras are gaining popularity as the sensor of choice for mobile robotics, due to their high performance in dynamic environments. However, these applications require efficient real-time data processing with low latency and power consumption. One strategy to meet these stringent requirements is hardware acceleration of efficient algorithms that preserve the temporal sparsity of event data. In this work, we propose an optimization strategy for Graph Convolutional Neural Networks models aimed at adapting their architecture to the limited resources of embedded heterogeneous FPGA platforms. Our method incorporates hardware-aware pruning and quantization, taking into account the trade-off between on-chip memory savings and inference accuracy. Strategic exploration of the design space with Fine Grid Search and Greedy layer-wise Iterative Deepening Search methods enables flexible adaptation of the model architecture to the target platform. Our approach was evaluated across various network configurations and multiple datasets, resulting in BRAM memory reductions of 28.8% for CIFAR-10 (with a 1.65% decrease in accuracy), 31.4% for MNIST-DVS (accuracy drop of 3.55%), and 26.5% for N-Caltech101 (with a 5.18% accuracy reduction).

Piotr Wzorek, Kamil Jeziorek, Tomasz Kryjak

Embedded Perception and Autonomous Systems Group, AGH University of Krakow, Poland

Event-Based Vision Graph Neural Networks Hardware-Aware NAS FPGA-Based Neural Network Acceleration Neural Network Pruning

Jul 7, 2026cs.CV

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising stages, ignoring the varying computational demands inherent to different noise levels. In this work, we propose a novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process. Unlike conventional post-hoc compression applied to a fixed diffusion pipeline, our approach jointly optimizes the denoising steps and structured model sparsity, transforming a pre-trained VDM into a compact, step-specific Mixture-of-Models (MoM). To address the training instability arising from this joint optimization, we introduce a Progressive Training Strategy coupled with an Output Rollout Mechanism, which ensures the coherent learning of structural decisions across timesteps. Furthermore, we develop a specialized inference engine to deploy the resulting MoM efficiently. Our method is orthogonal to existing acceleration techniques and highly effective: On Wan-14B, it removes 24% of the per-step FLOPs on top of 4-step distillation, adding a 1.2x wall-clock gain and reaching a 30x speedup over the 50-step teacher while preserving competitive generation quality.

Yu Cheng, Siyue Yao, Zhongang Qi +3

Zhejiang University · BlueImage, vivo · Westlake University

Video Diffusion Models Diffusion Model Distillation Few-Step Diffusion Sampling Diffusion Model Inference Acceleration Neural Network Pruning

Jul 4, 2026cs.CV

Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective

While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reductions in model size. Depth pruning, which removes entire layers from a ViT, is notoriously difficult for accuracy recovery despite its potential to deliver higher speedups, limiting the acceleration achieved by existing joint width-and-depth pruning methods. In this work, we reveal that the failure of existing depth pruning methods lies in their neglect of heterogeneity between different layers, and we introduce HetDPT, a heterogeneity-aware depth pruning method that avoids dimension mismatch. Comprehensive experiments on ImageNet-1K, CIFAR-100, COCO, and ADE20K validate our method: HetDPT achieves a 1.58

\times

speedup for DeiT-B while maintaining accuracy and a 1.39

\times

speedup for DeiT-S with nearly no accuracy degradation. Furthermore, when combined with width pruning, HetDPT+ sets a new state-of-the-art record in extreme ViT pruning, enhancing the acceleration ratio from 4.24

\times

to 5.19

\times

for the Isomorphic-Pruning-2.6G configuration while maintaining near-lossless accuracy; our code is available at https://github.com/Efficient-AI-for-All/HetDPT.

Zhenfeng Su, Kang Zhao, Han Bao +4

School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · Huawei Technologies Co., Ltd., Shenzhen, China · Tsinghua University, Beijing, China +1

Vision Transformer Efficient ViTs Neural Network Pruning

Jul 2, 2026cs.CV

When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression

Vision Transformers (ViTs) are strong backbones for semantic segmentation, but their computational cost limits deployment. Recent token compression methods for efficient transformer-based segmentation reduce this cost by decreasing the number of tokens. However, existing evaluations primarily focus on low-to-moderate compression, leaving their behavior under aggressive compression and corrupted inputs unclear. Meanwhile, structural pruning provides an orthogonal route to efficiency by removing redundant components in the ViT architecture, but is rarely compared to token compression under a unified protocol. To bridge this gap, we benchmark representative token compression and structural pruning methods for ViT-based semantic segmentation under matched FLOPs on ADE20K and Cityscapes, together with their common-corruption variants ADE20K-C and Cityscapes-C. Our results reveal a consistent trend on both clean and corrupted inputs: token compression is highly effective at mild reductions but degrades sharply when compression becomes severe, consistent with substantial information loss from overly aggressive token reduction. In contrast, structural pruning exhibits a smoother degradation curve and is more stable at high compression. Motivated by these findings, we study a prune-then-merge pipeline that applies moderate token compression on top of a moderately pruned backbone. At comparable FLOPs, this combined strategy consistently achieves a better accuracy-robustness trade-off at high compression, offering a practical recipe for deployment-oriented ViT segmentation. Code is available at https://github.com/phatnguyencs/vit-seg-compression.

Tien-Phat Nguyen, Ngai-Man Cheung

Temasek Laboratories, Singapore University of Technology and Design, Singapore

Distribution Shift Robustness Vision Transformer Efficient ViTs Corruption Robustness Semantic Segmentation Visual Token Compression+1

Jul 2, 2026cs.AI

Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns. We propose \textbf{Generic TB-Coverage}, a coverage-aware expert pruning method that uses only generic text corpora (WikiText2 and C4) for calibration. Instead of collapsing expert utility into one score, our method profiles per-expert utility separately on each corpus and enforces a fixed-budget coverage rule that preserves high-utility experts from each corpus before constructing the final pruning mask. Across Qwen1.5-MoE-A2.7B and DeepSeek-MoE-16B-Base at 25%, 50%, and 75% retention budgets, our method improves average accuracy on six common zero-shot benchmarks over random pruning, REAP, and ExpertSparsity, while also reducing perplexity degradation on WikiText2 and C4. The gains are largest under aggressive pruning (25% and 50% retain), suggesting that preserving cross-corpus expert coverage is an effective generic-data prior for MoE pruning. Our improvements hold with fixed pruning budgets and no downstream calibration data.

Yongqin Zeng, Sicheng Pan, Jiale Wang +4

Mixture-of-Experts Pruning LLM Pruning Mixture-of-Experts Language Models Sparse Mixture-of-Experts Neural Network Pruning

Jul 1, 2026cs.LG

On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain

Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network must remain loaded. Structured expert pruning is a practical approach for reducing deployment costs in resource-constrained settings. However, prior studies primarily evaluate benchmark utility, leaving the effect of pruning on factual reliability underexplored, particularly in high-stakes domains such as biomedicine. In this paper, we investigate how domain-specific expert pruning affects both utility and reliability. We assess four MoE models, six pruning methods, and multiple pruning ratios across generation and classification tasks under in-domain (biomedical) and cross-domain settings. Results reveal that moderate pruning preserves in-domain utility without immediate reliability decline, although hallucination risks increase at extreme pruning ratios. When shifting to the general domain, both utility and reliability degrade rapidly. These findings indicate that safe compression depends heavily on the task and domain. Evaluating pruned MoE models solely on utility is inadequate for high-stakes deployment without reliability assessment.

Atsuki Yamaguchi, Szymon Palucha, Léo Bijar +2

University of Sheffield, United Kingdom · AstraZeneca · University of Exeter, United Kingdom +1

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

Jul 1, 2026cs.CV

Post-Training Pruning for Diffusion Transformers

Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and parameter distribution, traditional pruning methods are inapplicable, leading to significant performance degradation. Specifically, prior methods developed for LLMs, which derive metrics through a series of approximations, amplify the relative contribution of weights in the saliency metric. In addition, weights in DiTs exhibit significantly larger magnitudes than those in LLMs. Moreover, existing pruning granularity overlooks variations in model structures. In this paper, we propose DiT-Pruning, which improves pruning performance by introducing customized saliency criteria and pruning granularity. We design a novel metric that balances the contributions of weights and activations from an energy-based perspective, enabling more effective identification of important elements. Furthermore, we observe distinct clustering patterns in the two-dimensional weight space. Accordingly, we adopt a clustering-aware pruning granularity, enabling effective sparse allocation. Extensive evaluations on various DiTs show that our method consistently preserves image quality, especially under high sparsity. For FLUX.1-dev at 512x512 resolution on MJHQ, DiT-Pruning achieves only a 0.001 loss in CLIP score at 50% sparsity, dramatically outperforming recent pruning methods.

Chengzhi Hu, Xuewen Liu, Jing Zhang +3

Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences

Diffusion Transformer Diffusion-Based Image Generation Diffusion Model Acceleration Neural Network Pruning

Jun 30, 2026cs.RO

Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation

Vision-Language-Action (VLA) models have made significant strides in embodied intelligence by integrating the powerful representations of pre-trained Vision-Language Models (VLMs). However, the massive parameter scale of VLAs imposes a heavy computational burden, and these models exhibit extreme sensitivity to parameter pruning. Current paradigms often treat the resulting performance degradation as inevitable, relying on fine-tuning or low-rank corrections to recover efficacy. We challenge this convention by questioning whether the removed parameters are truly redundant if VLA pruning necessitates performance recovery to be effective, or if this paradigm masks the indiscriminate pruning of critical parameters. We revisit parameter redundancy through the lens of VLM-to-VLA adaptation, first quantifying the spatial distribution of parameter divergence during adaptation to reveal structured patterns across different modules. Subsequently, we introduce controlled pruning as a diagnostic probe: by comparing the direct impact of removing different parameter subsets on VLA performance without any fine-tuning, we establish a causal link between adaptation-induced divergence signals and functional contributions. Based on the discovered modular heterogeneities, we design a multi-module joint pruning scheme. Evaluations on the LIBERO benchmark demonstrate that our approach reduces the parameters of OpenVLA and

π_{0.5}

by 12%--30% while maintaining approximately 90% of the original performance without any post-pruning recovery. In contrast, existing parameter pruning criteria result in total performance collapse when evaluated under the same recovery-free constraints. Our study reveals the parameter evolution mechanism in VLA adaptation and provides a new path for deploying efficient, robust robotic policies in resource-constrained environments.

Fengnian Zhang, Tao Huang, Siyu Xu +2

Computer Network Information Center, Chinese Academy of Sciences · University of Chinese Academy of Sciences · School of Computer Science, Shanghai Jiao Tong University +1

VLM Adaptation Vision-Language-Action Models Neural Network Pruning

Jun 26, 2026cs.AR

Co-Optimization of Analog Kolmogorov-Arnold Networks for Low-Power Function Approximation in Flexible Electronics

Wearable devices and Internet of Things (IoT) sensors require on-sensor processing of biosignals and environmental data, including computationally demanding operations such as nonlinear activation functions for neural network inference, sensor calibration curves to map raw readings to physical units, and signal preprocessing functions like logarithmic compression and power operations for feature extraction. These functions exhibit significant complexity, often involving transcendental operations and multivariate dependencies that are costly to implement digitally. Analog function approximation provides a power-efficient alternative by performing these computations in the analog domain, thereby reducing the energy overhead associated with analog-to-digital conversion and subsequent digital processing. Flexible Electronics (FE) present a particularly attractive platform for wearable applications due to mechanical flexibility and low-cost fabrication, but impose strict constraints on circuit density and power consumption, making efficient analog implementations critical but challenging. This work introduces Analog Kolmogorov-Arnold Networks (AKANs), developed via hardware-software co-optimization, to approximate these complex multivariate functions accurately under hardware imperfections. Our method incorporates circuit-level error modeling during training and applies pruning at both software and hardware levels to reduce area and power. Validation across multiple benchmarks demonstrates that our proposed pruning methodology not only reduces hardware cost but can also improve approximation accuracy by regularizing spline parameters. Results show up to 55% area and 50% power savings, with average reductions of nearly 30% across datasets, highlighting AKANs as a robust and generalizable framework for low-power analog function approximation in FE.

Paula Carolina Lozano Duarte, Georgios Zervakis, Mehdi Tahoori +1

Dept. of Computer Science, Karlsruhe Institute of Technology, Karlsruhe 76131, Germany · School of Electrical and Computer Engineering, National Technical University of Athens, Greece · Radyalis LLC, USA

Energy-Efficient ML Kolmogorov-Arnold Networks Hardware-Software Co-Design Neural Network Pruning

Jun 26, 2026cs.NE

Criticality-Constrained Iterative Pruning for Energy-Efficient Spiking Neural Networks via Combined Importance Scoring

Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity. Existing strategies either neglect neuronal criticality or rely on convex relaxations of the inherently combinatorial pruning problem whose fractional masks, upon binarisation, destroy accuracy at moderate-to-high sparsity. We present Criticality-Constrained Quadratic Pruning (CQP), a native PyTorch pipeline that fuses weight magnitude with surrogate-gradient criticality into an analytically exact importance metric, eliminating the rounding artefacts endemic to solver-based approaches. We formally characterise a continuous-relaxation trap wherein OSQP-solver fractional masks overshoot the intended sparsity by up to 12 percentage points (pp), precipitating a 44 pp accuracy collapse. We identify and remediate a zombie-weight failure mode in which Adam's first-moment tensors resurrect pruned synapses, violating the binary sparsity guarantee. An iterative schedule - prune, fine-tune with gradient masking, recompute criticality, and repeat - eliminates gradient staleness at high sparsity. A KL-divergence temporal analysis identifies a redundant simulation timestep, enabling a free 10% theoretical energy reduction without weight modification. On MNIST (60,000 training examples), CQP yields 95.6% accuracy at 90% sparsity versus 93.4% for magnitude pruning (+2.2 pp). A criticality-threshold sweep reveals an empirical criticality cliff: accuracy falls from 87.0% to 14.4% as the threshold reaches tau = 0.9, constituting a quantitative SNN-level analogue of the Critical Brain Hypothesis. Combined weight sparsification and temporal truncation yield a compound 73% reduction in per-inference energy at 70% sparsity, confirming the practical value of the proposed pipeline for neuromorphic deployment.

Muhammad Hamza

Indian Institute of Technology Kharagpur, West Bengal 721302, India

Efficient Neural Network Inference Spiking Neural Networks Neuromorphic Computing Neural Network Pruning

Jun 25, 2026cs.CV

TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing

Modern image generation model rapidly grows their sizes to meet high-fidelity image synthesis. However, they gradually become unaffordable for their enormous parameter consumption and computation budget that lead to massive resources requirement and gpu memory footprint. In this paper, we propose TMP, the first Tree-structured Mixed-policy Pruning framework that generalizes prevalent image tasks (T2I and TI2I) and architectures (Mixture-of-Experts (MoE) and Diffusion transformer (DiT)). It could be applied to the step-distilled models and contribute as the last stage. We perform experiments upon current open-sourced SOTA HunyuanImage-3.0 instruct and a popular efficient model Z-Image turbo. The proposed pruning framework manages to compress HunyuanImage 3.0 from 80B to 20B parameters at 75% reduction ratio, sacrificing limited generation quality. We also optimize to enable the inference of the pruned 20B version of HunyuanImage 3.0 on a single 24GB 4090 GPU by engineering skills. The inference script and model weight have been integrated into the existing HunyuanImage3.0 open-source github and huggingface repository. Besides, we prove the efficacy of TMP by compressing Z-Image turbo from 6B to 4B (33% reduction) with negligible degradation.

Peizhen Zhang, Yang Li, Xunsong Li +10

Multimodal Model Department, Tencent

Model Compression Diffusion-Based Image Generation T2I Diffusion Models Neural Network Pruning

Jun 25, 2026cs.LG

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value. We present two efficiency methods that exploit this asymmetry. CascadeFormer tapers width with depth to match the uneven information flow across layers, achieving comparable perplexity to a uniform baseline at the same training budget while reducing latency by 8.6% and increasing throughput by 9.4%. CascadeFlow Pruning removes layers using accumulated training gradients, with no post hoc analysis. It outperforms standard heuristics on perplexity and rank-stability and stays competitive on downstream accuracy. To motivate these methods, we propose Gradient Fan-in Asymmetry (GFA) as a structural account of why deeper layers contribute less. In Pre-LayerNorm residual stacks, the gradient at a layer is the sum of an identity path and all downstream functional paths, producing a gradient fan-in that decays linearly with depth (and quadratically under deep supervision), yielding richer gradients for early layers and sparser ones for later layers. We provide correlational and interventional evidence for GFA on models trained from scratch up to 1.2B parameters. Across Transformers and ResNets, accumulated training gradients follow the theoretical fan-in and are associated with post hoc layer importance. Two interventions point to structure rather than magnitude as the bottleneck: equalizing per-layer gradient norms does not restore late-layer value, while increasing downstream path counts via parameter-shared repetition restores and elevates it. Whether gradient magnitude proxies fan-in beyond high-rank regimes, and how these dynamics behave at the 100B+ scale, remain open questions.

Huzama Ahmad, Cao Viet Hai Nam, Se-Young Yun

KAIST

Efficient Transformer Inference Transformer Neural Network Pruning

Jun 25, 2026cs.LG

What Survives When You Compress a Recursive Reasoner for the Edge?

Recursive reasoning models solve hard structured tasks with a few million parameters by iterating a latent state, but deploying them on edge hardware means compressing them -- and quantization noise compounds across recursive cycles rather than accumulating over output tokens, so single-pass intuitions fail. Here, we ask what survives. Across a full precision sweep and three tasks, aggressive compression preserves local prediction but destroys global reasoning: pruning, distillation, and linear attention drive puzzle-exact accuracy to zero while cell accuracy holds. Naive INT4 is different: its damage is architectural, striking MLP-mixing recursion but not attention on the same task, and per-channel calibration reverses it without retraining, where quantization-aware training does not. We also introduce carry-trajectory fidelity, the cosine similarity to the full-precision reasoning path, as a label-free signal that predicts both the damage and the recovery before any task evaluation, with a threshold that transfers across tasks. The result is a deployment recipe: flash-streamed embeddings remove a 99.4 MB bottleneck, one recursive cycle matches full-depth accuracy at 6x fewer FLOPs, and calibrated INT4 brings the backbone to 3.3 MB, inside a 4 MB budget.

Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2

ML Collective · Carnegie Mellon University

Model Compression Efficient Neural Network Inference Structured Reasoning Neural Network Quantization Neural Network Pruning

Jun 24, 2026cs.LG

Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity, while high-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates. To mitigate the computational cost of policy evaluation, an iterative active learning loop interleaves surrogate-guided RL optimization with post-compression fine-tuning, using a lightweight MLP surrogate to amortize expensive evaluations and a logit-MSE proxy during cold-start. The surrogate is used for reward shaping rather than as a replacement for final post-compression evaluation. The controller is architecture-agnostic by design, with a modular layer abstraction decoupling the RL environment from the underlying network topology. Experiments across Vision Transformer and CNN benchmarks demonstrate effective parameter-storage compression ratios of 5.99 - 6.72

\times

with a 3.83 % gain in one setting and 0.55 - 5.62 % accuracy drops elsewhere, supporting hierarchical policy decomposition and sensitivity-aware guidance as practical design choices for joint neural network compression.

Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj +2

aNational School of Artificial Intelligence (ENSIA), Sidi Abdellah Campus, Algiers, Algeria · bCosys-Grettia, Univ Gustave Eiffel, F-77454 Marne-la-Vallee, France. · aNational School of Artificial Intelligence (ENSIA), Sidi Abdellah

Hierarchical RL Neural Network Quantization Neural Network Compression Neural Network Pruning

Jun 24, 2026cs.LG

EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression

Post-Training Sparsity (PTS) has emerged as a crucial paradigm for compressing Large Language Models to facilitate efficient deployment on resource-constrained devices. However, existing PTS methodologies are typically confined to Single-Sparsity optimization, necessitating a separate, time-consuming optimization session for each specific sparsity level. This rigid paradigm significantly hinders flexible deployment across diverse hardware scenarios, as adapting to a new sparsity requirement mandates a complete re-optimization process. To address these limitations, we propose Elastic Post-Training Sparsity (EPTS), a unified Multi-Sparsity framework that produces a single elastic model capable of maintaining robust performance across diverse sparsity configurations through a one-shot optimization process. Specifically, we design a Multi-Sparsity Hierarchy LoRA (MS-HiLoRA) mechanism that facilitates knowledge inheritance from low- to high-sparsity groups, effectively mitigating the competition for parameter reconstruction. Furthermore, we introduce a Multi-Sparsity Feature Mixer (MSFM), which significantly enhances the model's adaptability to pruning perturbations by dynamically fusing feature representations of varying sparsity granularities. Extensive experiments on LLaMA and OPT families demonstrate that EPTS achieves competitive performance compared to state-of-the-art methods like SparseGPT and Wanda, while offering significant efficiency gains by enabling multi-scenario deployment from a single optimization. our source code is available at https://github.com/xuke225/EPTS.

Ke Xu, Jiaqi Wan, Wenhao Hu +2

LLM Pruning LLM Compression Neural Network Pruning

Jun 23, 2026cs.RO

Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding

The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) tasks increasingly critical. Weight pruning techniques developed for VLMs to shrink model size and computation can be readily applied to satisfy the efficiency demands of on-board processing and real-time interactive robotics. Moreover, safe human-robot interaction demands pruning strategies that preserve doubly-correct predictions; outputs must be both accurate and evidentially grounded to mitigate risks and ensure user trust. In this paper, we present a new study of VLM pruning through the lens of doubly-correct prediction. Our experiments surprisingly show that existing pruning methods often preserve the right evidence localization but undermine correct prediction. To address this, we propose a rationale-informed pruning strategy that better aligns evidence with decisions. Benchmark results on egocentric video datasets demonstrate that our method not only achieves the highest prediction accuracy but also outperforms existing approaches in attaining doubly-correct predictions. We aim to stimulate research on efficient and reliable VLMs, ensuring accuracy-driven advances align with the transparency, auditability, and safety required for responsible human-robot interaction and embodied intelligence.

Qitong Wang, Fan Du, Pranav Maneriker +2

Dolby Laboratories, Inc., 1275 Market St, San Francisco, California, 94103, USA · Department of Computer and Information Sciences at the University of Delaware, Newark, DE 19711, USA · Dolby Laboratories, Inc.

Efficient VLM Inference Egocentric Vision VLMs for Robotics Neural Network Pruning

Jun 23, 2026cs.LG

Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration

Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.

Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1

University of Copenhagen Copenhagen, Denmark · LUT University Lahti, Finland

LLM Pruning LLM Interpretability Language Model Calibration Neural Network Pruning

Jun 22, 2026cs.LG

SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression

Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and compute requirements. Low-rank compression via singular value decomposition (SVD) is an effective remedy, but existing methods focus on how to factorize and which components to keep. We introduce SVD-Surgeon, a training-free method that brings the Optimal Brain Surgeon (OBS) framework to the singular-value basis. Treating each singular value as a parameter, it computes a closed-form update of the retained singular values that compensates, to second order in the model loss, for those removed by truncation. The same analysis yields a saliency for choosing which values to prune. As it operates directly on the singular-value factorization, SVD-Surgeon can be layered on top of existing SVD compressors. Applied to SVD-LLM, a leading SVD-based method, it improves the perplexity-compression trade-off on the OPT family and LLaMA 2-7B without any retraining.

Mahmoud Safari, Frank Hutter

University of Freiburg · Prior Labs · ELLIS Institute Tübingen

LLM Pruning LLM Compression Low-Rank Matrix Decomposition Low-Rank Compression Low-Rank Approximation Singular Value Decomposition+1

Jun 22, 2026cs.LG

Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization

Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ) samples in real time. At the same time, increasingly expressive deep neural networks (DNNs) are needed for robust interference classification and characterization across diverse signal conditions. This creates a fundamental tension between predictive performance and deployability on resource-constrained hardware. In this paper, we investigate efficient network inference for GNSS interference characterization using iterative structured pruning, post-training static quantization, and hardware-aware zero-shot neural architecture search (NAS). Starting from MCUNet as a compact baseline, we analyze how model compression and automated architecture optimization affect model size, computational complexity, and memory usage while maintaining task performance. Experiments on a GNSS interference dataset, covering both classification and generalized characterization, show the benefits of combining compression and hardware-aware design for embedded deployment. Our results provide practical guidance for developing compact machine learning (ML) models for real-time GNSS interference monitoring on embedded platforms (iMXRT1062 MCU, Raspberry Pi Zero 2W, and Raspberry Pi 5).

Lucas Heublein, Mark Deutel, Axel Plinge +1

Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany

Efficient Neural Network Inference Hardware-Aware NAS Post-Training Quantization Neural Network Pruning

Jun 22, 2026cs.LG

PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models

Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it remains unclear whether all latent channels contribute equally to the diffusion process, or whether significant redundancy exists. We introduce PeLAP-A (Adaptive Latent Pruning for Diffusion), a lightweight framework that augments a standard latent diffusion pipeline with a learnable channel-wise importance predictor. A two-layer MLP operating on globally pooled latent features produces a soft mask that suppresses unimportant latent channels before they enter the denoising UNet. The entire system is trained jointly on CIFAR-10 under a combined diffusion, reconstruction, and sparsity loss. Experiments reveal a striking result: under aggressive sparsity regularization (lambda = 0.01), the importance predictor drives all latent channels to near-zero yet the denoising UNet achieves lower diffusion loss (0.0236 vs. 0.0240) and lower VAE reconstruction MSE (22.59 vs. 24.67) compared to the unpruned baseline. We term this the sparsity collapse phenomenon and provide an analysis of why it occurs and what it reveals about the information requirements of latent diffusion models. These findings constitute an exploratory study of sparsity dynamics in latent diffusion training, and demonstrate that denoising UNets can remain remarkably robust to latent channel suppression even under aggressive regularization. Code is available at: https://github.com/kissasium/PeLAP-A.git.

Kissa Zahra, Zaib Un Nisa

Department of Computer Science, National University of Computer and Emerging Sciences

Latent Diffusion Models Neural Network Pruning

Jun 18, 2026cs.RO

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference. In this work, we reveal a highly non-trivial architectural characteristic of these continuous control foundation policies (e.g., pi_0, GR00T-N1.5): despite being trained on diverse physical trajectories, they exhibit severe layer-wise representational redundancy. To exploit this, we introduce a structural compression pipeline that is entirely training-free, bypassing the need of existing methods to load full-scale models to learn optimized token reductions or dynamic layer selectors. Instead, using only a single forward pass via Centered Kernel Alignment to identify redundant layer features, we remove twin layers to permanently compress the model depth by up to 50% across both the VLM backbone and the continuous control policy head. Downstream fine-tuning of this streamlined architecture yields a dual acceleration benefit: a 40-50% reduction in training time and up to 30% faster real-time inference, while matching or exceeding full-scale base model performance. We comprehensively validate our method across three simulation benchmarks (LIBERO, RoboCasa, SimplerEnv) and 10 diverse real-world manipulation tasks across 4 unique robotic embodiments. These results prove that advanced VLAs require significantly fewer layers than previously assumed, offering a highly compute-efficient paradigm for scalable robot learning.

Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18

Center for AI Research, VinUniversity · VinRobotics · University of Arkansas +10

Model Compression Efficient VLA Model Inference Efficient VLA Models Robotic Manipulation Vision-Language-Action Models Neural Network Pruning

Jun 17, 2026cs.LG

Complementary Attention Head Pruning for Efficient Transformers

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments. While structured pruning offers a pathway to compression, existing state-of-the-art methods often rely on gradient-based importance ranking or stochastic gating, which suffer from instability, structural degeneration, and the need for extensive manual hyperparameter tuning. In this paper, we introduce CAHP (Complementary Attention Head Pruning), a novel post-hoc framework that redefines head selection as a global graph-theoretical problem. Rather than evaluating heads in isolation, CAHP utilizes graph-based clustering combined with information-theoretic distance measures to identify and preserve a topologically diverse subset of complementary attention heads. Without requiring a predefined sparsity level or pruning ratio, the framework automatically determines the number of selected attention heads across layers by identifying a diminishing marginal performance curve, where pruning additional heads leads to a sharp degradation in performance, as determined by the chosen polynomial degree. Extensive evaluations on the SST-5 and MNLI benchmarks, across different Transformer model scales, demonstrate that CAHP consistently outperforms competitive baselines, particularly in high-compression regimes. Furthermore, our structural analysis shows that CAHP avoids the "proximity bias" of gradient-based pruning methods, which tend to preserve heads mainly in layers close to the output, and instead retains a functionally critical set of attention heads in the model's intermediate layers.

Yaniv Livertovsky, Shahar Somin, Gonen Singer

Bar-Ilan University Ramat Gan, Israel

Model Compression Transformer Attention Attention Head Pruning Neural Network Pruning

Jun 16, 2026cs.LG

S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained Devices

Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data. Despite their strong empirical performance, deploying these models in time- and resource-constrained settings remains challenging due to their computational and memory demands. In this paper, we propose a novel incremental, operator-level pruning approach for S4- and S4D-based models that significantly reduces inference cost while preserving predictive performance. To the best of our knowledge, this is the first work to systematically investigate structured operator pruning for SSMs. Our method progressively prunes model operators by interleaving structured masking with fine-tuning, while jointly monitoring accuracy and inference latency. We implement this approach within a unified training and evaluation framework that enables systematic exploration of efficiency-accuracy trade-offs. Experiments across multiple benchmark datasets show that pruning up to 70% of the model operators preserves the performance of the original models in most cases, while substantially reducing inference latency. These results demonstrate that structured operator pruning is an effective and previously unexplored strategy for improving the efficiency of SSMs and facilitate their deployment in practical, resource-constrained scenarios.

Marco Deano, Filippo Ziche, Nicola Bombieri

University of Verona Italy

Efficient Neural Network Inference Neural Network Pruning State Space Models