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

All topics

Searching for Task-Specific Vision Paths: Evolutionary Block Pruning Across Vision-Language Models
Jul 19, 2026Tarun TomarEfficient VLM Inference Neural Network Pruning
Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding
Jul 18, 2026Anik JhaMixture-of-Experts Pruning Mixture-of-Experts Language Models
1Independent Researcher
Efficient Text-to-Audio Generation via Pruning
Jul 14, 2026Arshdeep Singh, Yi Yuan, Yun Chen +2Text-to-Audio Generation Latent Diffusion Models
1King’s College London (KCL) · University of Surrey, UK
An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals
Jul 13, 2026Raktim BhattacharyaSelective SSMs Neural Network Pruning
Aerospace Engineering, Texas A&M University
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
Jul 13, 2026Hao Kong, Di Liu, Xiangzhong Luo +5Efficient Neural Network Inference Convolutional Neural Networks
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
WaveNet-Style Guitar Amplifier Model Pruning for Real-Time iOS Deployment
Jul 11, 2026Ryota Sato, Eli SilversteinEfficient Neural Network Inference On-Device Inference
Dept. of Electrical Engineering Stanford University Stanford, USA
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
Jul 8, 2026Yazdan Jamshidi, Alexey ShvetsLLM Pruning LLM Compression
Palo Alto Networks
Hardware-aware Graph Neural Networks prunning for embedded event-based vision
Jul 7, 2026Piotr Wzorek, Kamil Jeziorek, Tomasz KryjakEvent-Based Vision Graph Neural Networks
Embedded Perception and Autonomous Systems Group, AGH University of Krakow, Poland
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
Jul 7, 2026Yu Cheng, Siyue Yao, Zhongang Qi +3Video Diffusion Models Diffusion Model Distillation
Zhejiang University · BlueImage, vivo · Westlake University
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
Jul 4, 2026Zhenfeng Su, Kang Zhao, Han Bao +4Vision Transformer Efficient ViTs
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · Huawei Technologies Co., Ltd., Shenzhen, China · Tsinghua University, Beijing, China +1
When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
Jul 2, 2026Tien-Phat Nguyen, Ngai-Man CheungDistribution Shift Robustness Vision Transformer
Temasek Laboratories, Singapore University of Technology and Design, Singapore
Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
Jul 2, 2026Yongqin Zeng, Sicheng Pan, Jiale Wang +4Mixture-of-Experts Pruning LLM Pruning
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
Jul 1, 2026Atsuki Yamaguchi, Szymon Palucha, Léo Bijar +2Mixture-of-Experts Pruning LLM Reliability
University of Sheffield, United Kingdom · AstraZeneca · University of Exeter, United Kingdom +1
Post-Training Pruning for Diffusion Transformers
Jul 1, 2026Chengzhi Hu, Xuewen Liu, Jing Zhang +3Diffusion Transformer Diffusion-Based Image Generation
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation
Jun 30, 2026Fengnian Zhang, Tao Huang, Siyu Xu +2VLM Adaptation Vision-Language-Action Models
Computer Network Information Center, Chinese Academy of Sciences · University of Chinese Academy of Sciences · School of Computer Science, Shanghai Jiao Tong University +1
Co-Optimization of Analog Kolmogorov-Arnold Networks for Low-Power Function Approximation in Flexible Electronics
Jun 26, 2026Paula Carolina Lozano Duarte, Georgios Zervakis, Mehdi Tahoori +1Energy-Efficient ML Kolmogorov-Arnold Networks
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
Criticality-Constrained Iterative Pruning for Energy-Efficient Spiking Neural Networks via Combined Importance Scoring
Jun 26, 2026Muhammad HamzaEfficient Neural Network Inference Spiking Neural Networks
Indian Institute of Technology Kharagpur, West Bengal 721302, India
TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing
Jun 25, 2026Peizhen Zhang, Yang Li, Xunsong Li +10Model Compression Diffusion-Based Image Generation
Multimodal Model Department, Tencent
CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry
Jun 25, 2026Huzama Ahmad, Cao Viet Hai Nam, Se-Young YunEfficient Transformer Inference Transformer
KAIST
What Survives When You Compress a Recursive Reasoner for the Edge?
Jun 25, 2026Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2Model Compression Efficient Neural Network Inference
ML Collective · Carnegie Mellon University
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
Jun 24, 2026Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj +2Hierarchical RL Neural Network Quantization
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
EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression
Jun 24, 2026Ke Xu, Jiaqi Wan, Wenhao Hu +2LLM Pruning LLM Compression
Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
Jun 23, 2026Qitong Wang, Fan Du, Pranav Maneriker +2Efficient VLM Inference Egocentric Vision
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.
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Jun 23, 2026Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1LLM Pruning LLM Interpretability
University of Copenhagen Copenhagen, Denmark · LUT University Lahti, Finland
SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression
Jun 22, 2026Mahmoud Safari, Frank HutterLLM Pruning LLM Compression
University of Freiburg · Prior Labs · ELLIS Institute Tübingen
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
Jun 22, 2026Lucas Heublein, Mark Deutel, Axel Plinge +1Efficient Neural Network Inference Hardware-Aware NAS
Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany
PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models
Jun 22, 2026Kissa Zahra, Zaib Un NisaLatent Diffusion Models Neural Network Pruning
Department of Computer Science, National University of Computer and Emerging Sciences
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Jun 18, 2026Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18Model Compression Efficient VLA Model Inference
Center for AI Research, VinUniversity · VinRobotics · University of Arkansas +10
Complementary Attention Head Pruning for Efficient Transformers
Jun 17, 2026Yaniv Livertovsky, Shahar Somin, Gonen SingerModel Compression Transformer Attention
Bar-Ilan University Ramat Gan, Israel
S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained Devices
Jun 16, 2026Marco Deano, Filippo Ziche, Nicola BombieriEfficient Neural Network Inference Neural Network Pruning
University of Verona Italy

Jul 19, 2026, cs.CVJ/K move · Enter open · S save

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

Tarun Tomar

Efficient VLM Inference Neural Network Pruning

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 161