Pruning

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

15 new papers

A weekly snapshot of new work published in Pruning.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Pruning.

Period ending 2026-09-07

9 new papers

A weekly snapshot of new work published in Pruning.

Inside this field

Focused directions

Focused topic

Pruning

Within Pruning

160 papersExplore

Focused topic

Visual Tokens

Within Pruning

140 papersExplore

Focused topic

Visual Token Pruning

Within Pruning

101 papersExplore

Focused topic

Heterogeneous Pruning Scores

Within Pruning

70 papersExplore

363 papers

Latest in Pruning

Browse all topics →

Squeeze-Release: Iterative Pruning with Exact Structural Minimization
Jun 12, 2026Roman Denkin, Ida Akerholm, Prashant Singh +1Heterogeneous Pruning Scores Pruning
One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs
Jun 12, 2026Yongru Chen, Kai Zhang, Zeliang Zong +4Visual Token Pruning Visual Tokens
Small LLMs: Pruning vs. Training from Scratch
Jun 12, 2026Yufeng Xu, Taiming Lu, Kunjun Li +3Small Language Models Pruning
Explainable Task-Oriented Token Communication for AI-Native 6G Networks
Jun 12, 2026Feibo Jiang, Lei Mao, Li Dong +3Semantic Communications Visual Tokens
Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantization
Jun 12, 2026Rishit Chatterjee, Tahiya ChowdhurySpeaker Diarization Neural Audio Codecs
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
Jun 11, 2026Junke Wang, Qihang Zhang, Shuai Yang +5Efficient World-Action Model World Models
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Jun 11, 2026Guozhen Zhang, Xuerui Qiu, Yutao Cui +11Visual Tokens Self-Supervised Vision Transformers
Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
Jun 11, 2026Dongyue Wu, Zilin Guo, Xiaoyu Li +4Heterogeneous Pruning Scores Graph Representation Learning
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
Jun 10, 2026Romana Qureshi, Hafida Benhidour, Said Kerrache +1Heterogeneous Pruning Scores Sparse Deep Neural Network Accelerators
The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models
Jun 10, 2026Chenyu Zhou, Qiliang Jiang, Shuning Wu +1Vision Encoders Visual Tokens
Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering
Jun 10, 2026Haoning Xu, Zhaoqing Li, Huimeng Wang +4Large Language Model Compression Speech Large Language Models
MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models
Jun 10, 2026Yuansheng Gao, Wenbin Xing, Jiahao Yuan +4Video Multimodal Large Language Models Visual Tokens
RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning
Jun 10, 2026Atif Hassan, Swanand Khare, Jiaul H. PaikHeterogeneous Pruning Scores Extreme Class Imbalance
Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning
Jun 9, 2026Zihan Meng, Dexiang Hong, Weidong Chen +3Visual Token Pruning Video Captioning
SpenseGPT: Practical One-shot Pruning Enabling Sparse and Dense GEMMs for LLM Inference
Jun 9, 2026Jaeseong Lee, Seung-won Hwang, Samyam RajbhandariSparsity LLM Inference Efficiency
Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
Jun 9, 2026Dahye Kim, Jaehyun Choi, Hyun Seok Seong +4Ai-Generated Image Detection Adversarial Examples
Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy
Jun 8, 2026Haozhe Hu, Hao Wu, Anhao Zhao +4Heterogeneous Pruning Scores LLM Inference Efficiency
REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance
Jun 8, 2026Zhang Chen, Shuai Wan, Mengting Yu +23D Gaussian Splats 3D Gaussian
Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning
Jun 7, 2026Jingzhi Chen, Landi He, Zhuo Chen +2Whole-Slide Images Visual Tokens
OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
Jun 7, 2026Chenhan Jin, Shengze Xu, Qingsong Wang +3Heterogeneous Pruning Scores Pruning
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
Jun 7, 2026Miracle Kang, Lights Shi, Lucy Liang +10Vision-Language-Action Models Visual Tokens
Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs
Jun 7, 2026Jie Ma, Zhike Qiu, Jiayi Ji +2Cross-Modal Attention Multi-Modal Large Language Models
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT
Jun 6, 2026Kyumin Choi, Ikbeom JangVisual Token Pruning Self-Supervised Vision Transformers
Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
Jun 5, 2026Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1Mixed-Precision Quantization Weight-Only Quantization
AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens
Jun 5, 2026Xiaocheng Lu, Yuxi Chen, Jie Zhang +5Visual Tokens Tokenization
MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models
Jun 5, 2026Yifan Xu, Chao Zhang, Ruifei Ma +4Pre-Trained Video Diffusion Models Visual Tokens
Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting
Jun 4, 2026Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das +3Token Compression Visual Tokens
Fast Cubical Persistent Homology on 2D and 3D Images via Union-Find, Pruning, and Lookup Tables
Jun 3, 2026Titouan Le Breton, Karol Szustakowski, Marie PiraudPersistent Homology Cubifygs
ChannelTok: Efficient Flexible-Length Vision Tokenization
Jun 3, 2026Sukriti Paul, Arpit Bansal, Tom GoldsteinVisual Tokens Tokenization
Differentiable Efficient Operator Search
Jun 3, 2026Xiaohuan Pei, Jiyuan Zhang, Yuanfan Guo +4Multimodal Foundation Model Visual Token Pruning
MLSkip: Data Skipping for ML Filters via Lightweight Metadata
Jun 2, 2026Mihail Stoian, Mark Gerarts, Pascal Ginter +3Skip Heterogeneous Pruning Scores
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Jun 2, 2026Senjie Jin, Peixin Wang, Boyang Liu +8Visual Reasoning Visual Tokens
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
Jun 2, 2026Tianxiong Zhong, Xingye Tian, Xuebo Wang +2Generative Models Diffusion Dynamics
When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
Jun 2, 2026Jiahui Wang, Kai Zhang, Mai Han +1Visual Token Pruning Visual Tokens
VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning
Jun 1, 2026Aoduo Li, Jiancheng Li, Huan Ye +53D Gaussian Splats Novel View Synthesis
Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning
Jun 1, 2026Ziyang Yao, Zeyu Zhu, YunCheng Jiang +2Autonomous Driving Visual Tokens
EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
Jun 1, 2026Hongyu Lu, Feng Zhang, Wenwei Jin +5Token Compression Visual Tokens
CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search
Jun 1, 2026Cheonjun ParkHeterogeneous Pruning Scores Large Language Model Post-Training
Neural Network Compression by Approximate Differential Equivalence
May 31, 2026Ravi Dhiman, Andrea Passarella, Mirco Tribastone +1Neural-Network Approximation Neural Network
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
May 31, 2026Mingxi LiGenerative Super-Resolution Calibration-Free Low-Bit Vector Quantization
ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs
May 30, 2026Yiling Gao, Hongchen Wei, Zhenzhong ChenToken Compression Visual Tokens
V-LynX: Token Interface Alignment for Video+X LLMs
May 30, 2026Jungin Park, Jiyoung Lee, Kwanghoon SohnVisual Tokens Modality-Specific Encoders
Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
May 29, 2026Salem Ameen, Sunil VaderaModern Deep Networks Heterogeneous Pruning Scores
VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
May 29, 2026Hengbo Xu, Shengjie Jin, Yanbiao Ma +1Multimodal Reasoning Visual Token Pruning
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
May 29, 2026Luyuan Zhang, Siyuan Li, Zedong Wang +7Visual Tokens Tokenization
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
May 28, 2026Selim Kuzucu, Alessio Tonioni, Vasile Lup +3Visual Tokens Token Compression
SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
May 28, 2026Shilin Ma, Chubin Zhang, Changyuan Wang +6Visual Token Pruning Vision-Language-Action Models
OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
May 28, 2026Geng Li, Guohao Chen, Ting Chen +6Visual Token Pruning Visual Tokens
AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference
May 28, 2026Yilin Feng, Ahmed Burak Gulhan, Mahmut Taylan KandemirVisual Token Pruning Visual Tokens
Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
May 27, 2026Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat +3Symbolic Regression Scientific Discovery
PrunePath: Towards Highly Structured Sparse Language Models
May 27, 2026Zhexuan Gu, Zixun Fu, Yancheng YuanPruning Sparsity
Pruning and Distilling Mixture-of-Experts into Dense Language Models
May 27, 2026Junhyuck Kim, Jihun Yun, Haechan Kim +3Mixture-Of-Expert Language Models Mixture-of-Experts Models
PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
May 27, 2026Haruki Yajima, Yusuke MatsuiDecision Trees Heterogeneous Pruning Scores
Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models
May 27, 2026Landi He, Mingde Yao, Shawn Young +1Visual Token Pruning Large Vision Language Models
Locality-Aware Redundancy Pruning for LLM Depth Compression
May 27, 2026Vincent-Daniel Yun, Youngrae Kim, Woosang Lim +3Large Language Model Compression Pruning
Structure over Pixels: Learning Variable-Length Visual Programs
May 26, 2026Piotr Wyrwiński, Kacper Dobek, Krzysztof KrawiecVisual Tokens Intermediate Scene Representations
PARE: Pruning and Adaptive Routing for Efficient Video Generation
May 26, 2026Yutong Wang, Yunke Wang, Tianfan Xue +4Generative Image Compression Pruning
Resource-Constrained Affect Modelling via Variance Regularisation Pruning
May 26, 2026Kosmas Pinitas, Konstantinos KatsifisAffective Computing Heterogeneous Pruning Scores
DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding
May 26, 2026Jianfei Zhao, Feng Zhang, Xin Sun +3Visual Tokens Fine-Grained Perception
Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling
May 26, 2026Fengfa Li, Hongjin Ji, Yifeng Ding +2Mixture-Of-Expert Inference Mixture-of-Experts Models

Jun 12, 2026 · cs.LGJ/K move · Enter open · S save

Squeeze-Release: Iterative Pruning with Exact Structural Minimization

Roman Denkin, Ida Akerholm, Prashant Singh, Ida-Maria Sintorn

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

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.

Heterogeneous Pruning Scores Pruning Batch Normalization Resnet-18 Flat Minima

Open paper Ask about it PDF