PaperListTemplate

Paper List Template

This template makes it easy for you to manage papers.

Paper List Template
- Table of Contents
- Getting Started

Getting Started

Add paper information by ./add_paper_info.sh or ./add_paper_info.sh <name>
Run ./refresh_readme.sh

sparsegpt.prototxt

``` paper { title: "SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot." abbr: "SparseGPT" url: "https://arxiv.org/pdf/2301.00774.pdf" authors: "Elias Frantar" authors: "Dan Alistarh" institutions: "IST Austria" institutions: "Neural Magic" } pub { where: "arXiv" year: 2023 } code { type: "Pytorch" url: "https://github.com/IST-DASLab/sparsegpt" } note { url: "SparseGPT.md" } keyword { words: "sparsity" } ```

Paper List

### keyword

Quantization

| | meta | title | publication | year | code | note | cover | |---:|:-----------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:------------------------------------------------|:-------|:--------| | 0 | [RPTQ](/PaperListTemplate/meta/RPTQ.prototxt) | [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://arxiv.org/pdf/2304.01089.pdf) | arXiv | 2023 | [PyTorch](https://github.com/hahnyuan/RPTQ4LLM) | | |

Sparse/Pruning

### year

2016

2021

| | meta | title | publication | year | code | note | cover | |---:|:-------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------|-------:|:-------|:-------|:--------| | 0 | [OpenVINO](/PaperListTemplate/meta/OpenVINO.prototxt) | [Post-training deep neural network pruning via layer-wise calibration](https://openaccess.thecvf.com/content/ICCV2021W/LPCV/papers/Lazarevich_Post-Training_Deep_Neural_Network_Pruning_via_Layer-Wise_Calibration_ICCVW_2021_paper.pdf) | ICCV workshop | 2021 | | | |

2023

| | meta | title |---:|:---------------------------------------|:-------- | 0 | [abbr](/PaperListTemplate/meta/BU38BOQE.prototxt) | 1 | [abbr](/PaperListTemplate/meta/SP5UN1RF.prototxt) | 2 | [abbr](/PaperListTemplate/meta/Q3S45CWC.prototxt) | 3 | [abbr](/PaperListTemplate/meta/JBRI286F.prototxt) | 4 | [abbr](/PaperListTemplate/meta/22C0A4RH.prototxt) | 5 | [abbr](/PaperListTemplate/meta/TVCZSVZY.prototxt) | 6 | [abbr](/PaperListTemplate/meta/ZHVKFNSL.prototxt) | 7 | [abbr](/PaperListTemplate/meta/9O673CMS.prototxt) | 8 | [abbr](/PaperListTemplate/meta/Q0PKEEPI.prototxt) | 9 | [abbr](/PaperListTemplate/meta/AZKA1WRH.prototxt) | 10 | [abbr](/PaperListTemplate/meta/RR92I0FK.prototxt) | 11 | [abbr](/PaperListTemplate/meta/CSUM4GXD.prototxt) | 12 | [MVUE](/PaperListTemplate/meta/2U5DXO7C.prototxt) | 13 | [NTK-SAP](/PaperListTemplate/meta/HYTID4WD.prototxt) | 14 | [OTOv2](/PaperListTemplate/meta/QBBMHBHQ.prototxt) | 15 | [abbr](/PaperListTemplate/meta/1EZ5JYL3.prototxt) | 16 | [abbr](/PaperListTemplate/meta/4IT9WPPA.prototxt) | 17 | [abbr](/PaperListTemplate/meta/GEZARAUL.prototxt) | 18 | [m](/PaperListTemplate/meta/0I1IQIH6.prototxt) | 19 | [abbr](/PaperListTemplate/meta/DLHYYZU1.prototxt) | 20 | [SMC](/PaperListTemplate/meta/EHWNTP1V.prototxt) | 21 | [m](/PaperListTemplate/meta/RRGOXITB.prototxt) | 22 | [abbr](/PaperListTemplate/meta/MTKTZE3N.prototxt) | 23 | [m](/PaperListTemplate/meta/R4X91L5N.prototxt) | 24 | [RPTQ](/PaperListTemplate/meta/RPTQ.prototxt) | 25 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | publication | year | code | note | cover | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------|-------:|:------------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | [A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis](https://openreview.net/forum?id=vVJZtlZB9D) | ICLR | 2023 | | | | | [A Unified Framework for Soft Threshold Pruning](https://openreview.net/forum?id=cCFqcrq0d8) | ICLR | 2023 | | | | | [Bit-Pruning: A Sparse Multiplication-Less Dot-Product](https://openreview.net/forum?id=YUDiZcZTI8) | ICLR | 2023 | | | | | [CrAM: A Compression-Aware Minimizer](https://openreview.net/forum?id=_eTZBs-yedr) | ICLR | 2023 | | | | | [DFPC: Data flow driven pruning of coupled channels without data](https://openreview.net/forum?id=mhnHqRqcjYU) | ICLR | 2023 | | | | | [DepthFL: Depthwise Federated Learning for Heterogeneous Clients](https://openreview.net/forum?id=pf8RIZTMU58) | ICLR | 2023 | | | | | [Diffusion Models for Causal Discovery via Topological Ordering](https://openreview.net/forum?id=Idusfje4-Wq) | ICLR | 2023 | | | | | [Holistic Adversarially Robust Pruning](https://openreview.net/forum?id=sAJDi9lD06L) | ICLR | 2023 | | | | | [HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers](https://openreview.net/forum?id=D7srTrGhAs) | ICLR | 2023 | | | | | [How I Learned to Stop Worrying and Love Retraining](https://openreview.net/forum?id=_nF5imFKQI) | ICLR | 2023 | | | | | [Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks](https://openreview.net/forum?id=4UldFtZ_CVF) | ICLR | 2023 | | | | | [MECTA: Memory-Economic Continual Test-Time Model Adaptation](https://openreview.net/forum?id=N92hjSf5NNh) | ICLR | 2023 | | | | | [Minimum Variance Unbiased N:M Sparsity for the Neural Gradients](https://openreview.net/pdf?id=vuD2xEtxZcj) | ICLR | 2023 | | | | | [NTK-SAP: Improving neural network pruning by aligning training dynamics](https://openreview.net/forum?id=-5EWhW_4qWP) | ICLR | 2023 | | | | | [OTOv2: Automatic, Generic, User-Friendly](https://openreview.net/forum?id=7ynoX1ojPMt) | ICLR | 2023 | [Pytorch](https://github.com/tianyic/only_train_once) | | | | [Over-parameterized Model Optimization with Polyak-Lojasiewicz Condition](https://openreview.net/forum?id=aBIpZvMdS56) | ICLR | 2023 | | | | | [Pruning Deep Neural Networks from a Sparsity Perspective](https://openreview.net/forum?id=i-DleYh34BM) | ICLR | 2023 | | | | | [Rethinking Graph Lottery Tickets: Graph Sparsity Matters](https://openreview.net/forum?id=fjh7UGQgOB) | ICLR | 2023 | | | | | [Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph](https://openreview.net/forum?id=uVcDssQff) | ICLR | 2023 | | | | | [Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective](https://openreview.net/forum?id=Dvs-a3aymPe) | ICLR | 2023 | | | | | [Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!](https://openreview.net/pdf?id=J6F3lLg4Kdp) | ICLR | 2023 | [SMC-Bench](https://github.com/VITA-Group/SMC-Bench) | | | | [Symmetric Pruning in Quantum Neural Networks](https://openreview.net/forum?id=K96AogLDT2K) | ICLR | 2023 | | | | | [TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning](https://openreview.net/forum?id=sZI1Oj9KBKy) | ICLR | 2023 | | | | | [Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?](https://openreview.net/forum?id=xSsW2Am-ukZ) | ICLR | 2023 | | | | | [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://arxiv.org/pdf/2304.01089.pdf) | arXiv | 2023 | [PyTorch](https://github.com/hahnyuan/RPTQ4LLM) | | | | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

### publication

ICCV workshop

ICLR

| | meta | title | publication | year | code | note | cover | |---:|:----------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------|-------:|:------------------------------------------------------|:-------|:--------| | 0 | [Deep Compression](/PaperListTemplate/meta/deepcompression.prototxt) | Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding | ICLR | 2016 | | | | | 1 | [abbr](/PaperListTemplate/meta/BU38BOQE.prototxt) | [A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis](https://openreview.net/forum?id=vVJZtlZB9D) | ICLR | 2023 | | | | | 2 | [abbr](/PaperListTemplate/meta/SP5UN1RF.prototxt) | [A Unified Framework for Soft Threshold Pruning](https://openreview.net/forum?id=cCFqcrq0d8) | ICLR | 2023 | | | | | 3 | [abbr](/PaperListTemplate/meta/Q3S45CWC.prototxt) | [Bit-Pruning: A Sparse Multiplication-Less Dot-Product](https://openreview.net/forum?id=YUDiZcZTI8) | ICLR | 2023 | | | | | 4 | [abbr](/PaperListTemplate/meta/JBRI286F.prototxt) | [CrAM: A Compression-Aware Minimizer](https://openreview.net/forum?id=_eTZBs-yedr) | ICLR | 2023 | | | | | 5 | [abbr](/PaperListTemplate/meta/22C0A4RH.prototxt) | [DFPC: Data flow driven pruning of coupled channels without data](https://openreview.net/forum?id=mhnHqRqcjYU) | ICLR | 2023 | | | | | 6 | [abbr](/PaperListTemplate/meta/TVCZSVZY.prototxt) | [DepthFL: Depthwise Federated Learning for Heterogeneous Clients](https://openreview.net/forum?id=pf8RIZTMU58) | ICLR | 2023 | | | | | 7 | [abbr](/PaperListTemplate/meta/ZHVKFNSL.prototxt) | [Diffusion Models for Causal Discovery via Topological Ordering](https://openreview.net/forum?id=Idusfje4-Wq) | ICLR | 2023 | | | | | 8 | [abbr](/PaperListTemplate/meta/9O673CMS.prototxt) | [Holistic Adversarially Robust Pruning](https://openreview.net/forum?id=sAJDi9lD06L) | ICLR | 2023 | | | | | 9 | [abbr](/PaperListTemplate/meta/Q0PKEEPI.prototxt) | [HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers](https://openreview.net/forum?id=D7srTrGhAs) | ICLR | 2023 | | | | | 10 | [abbr](/PaperListTemplate/meta/AZKA1WRH.prototxt) | [How I Learned to Stop Worrying and Love Retraining](https://openreview.net/forum?id=_nF5imFKQI) | ICLR | 2023 | | | | | 11 | [abbr](/PaperListTemplate/meta/RR92I0FK.prototxt) | [Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks](https://openreview.net/forum?id=4UldFtZ_CVF) | ICLR | 2023 | | | | | 12 | [abbr](/PaperListTemplate/meta/CSUM4GXD.prototxt) | [MECTA: Memory-Economic Continual Test-Time Model Adaptation](https://openreview.net/forum?id=N92hjSf5NNh) | ICLR | 2023 | | | | | 13 | [MVUE](/PaperListTemplate/meta/2U5DXO7C.prototxt) | [Minimum Variance Unbiased N:M Sparsity for the Neural Gradients](https://openreview.net/pdf?id=vuD2xEtxZcj) | ICLR | 2023 | | | | | 14 | [NTK-SAP](/PaperListTemplate/meta/HYTID4WD.prototxt) | [NTK-SAP: Improving neural network pruning by aligning training dynamics](https://openreview.net/forum?id=-5EWhW_4qWP) | ICLR | 2023 | | | | | 15 | [OTOv2](/PaperListTemplate/meta/QBBMHBHQ.prototxt) | [OTOv2: Automatic, Generic, User-Friendly](https://openreview.net/forum?id=7ynoX1ojPMt) | ICLR | 2023 | [Pytorch](https://github.com/tianyic/only_train_once) | | | | 16 | [abbr](/PaperListTemplate/meta/1EZ5JYL3.prototxt) | [Over-parameterized Model Optimization with Polyak-Lojasiewicz Condition](https://openreview.net/forum?id=aBIpZvMdS56) | ICLR | 2023 | | | | | 17 | [abbr](/PaperListTemplate/meta/4IT9WPPA.prototxt) | [Pruning Deep Neural Networks from a Sparsity Perspective](https://openreview.net/forum?id=i-DleYh34BM) | ICLR | 2023 | | | | | 18 | [abbr](/PaperListTemplate/meta/GEZARAUL.prototxt) | [Rethinking Graph Lottery Tickets: Graph Sparsity Matters](https://openreview.net/forum?id=fjh7UGQgOB) | ICLR | 2023 | | | | | 19 | [m](/PaperListTemplate/meta/0I1IQIH6.prototxt) | [Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph](https://openreview.net/forum?id=uVcDssQff) | ICLR | 2023 | | | | | 20 | [abbr](/PaperListTemplate/meta/DLHYYZU1.prototxt) | [Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective](https://openreview.net/forum?id=Dvs-a3aymPe) | ICLR | 2023 | | | | | 21 | [SMC](/PaperListTemplate/meta/EHWNTP1V.prototxt) | [Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!](https://openreview.net/pdf?id=J6F3lLg4Kdp) | ICLR | 2023 | [SMC-Bench](https://github.com/VITA-Group/SMC-Bench) | | | | 22 | [m](/PaperListTemplate/meta/RRGOXITB.prototxt) | [Symmetric Pruning in Quantum Neural Networks](https://openreview.net/forum?id=K96AogLDT2K) | ICLR | 2023 | | | | | 23 | [abbr](/PaperListTemplate/meta/MTKTZE3N.prototxt) | [TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning](https://openreview.net/forum?id=sZI1Oj9KBKy) | ICLR | 2023 | | | | | 24 | [m](/PaperListTemplate/meta/R4X91L5N.prototxt) | [Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?](https://openreview.net/forum?id=xSsW2Am-ukZ) | ICLR | 2023 | | | |

arXiv

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:---------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | 0 | [RPTQ](/PaperListTemplate/meta/RPTQ.prototxt) | [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://arxiv.org/pdf/2304.01089.pdf) | arXiv | 2023 | [PyTorch](https://github.com/hahnyuan/RPTQ4LLM) | | | | 1 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

### instution

Eindhoven University of Technology

| | meta | title | publication | year | code | note | cover | |---:|:--------------------------------|:----------------------------------------------------------------------------------------------------------------------|:--------------|-------:|:-----------------------------------------------------|:-------|:--------| | 0 | [SMC](/PaperListTemplate/meta/EHWNTP1V.prototxt) | [Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!](https://openreview.net/pdf?id=J6F3lLg4Kdp) | ICLR | 2023 | [SMC-Bench](https://github.com/VITA-Group/SMC-Bench) | | |

Habana Labs

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------|:-------------------------------------------------------------------------------------------------------------|:--------------|-------:|:-------|:-------|:--------| | 0 | [MVUE](/PaperListTemplate/meta/2U5DXO7C.prototxt) | [Minimum Variance Unbiased N:M Sparsity for the Neural Gradients](https://openreview.net/pdf?id=vuD2xEtxZcj) | ICLR | 2023 | | | |

Houmo AI

IST Austria

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:---------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | 0 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

Intel Corporation

Neural Magic

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:---------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | 0 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

Stanford University

Tencent AI Lab

University of Texas at Austin

inst1

| | meta | title | publication | year | code | note | cover | |---:|:------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------|-------:|:------------------------------------------------------|:-------|:--------| | 0 | [abbr](/PaperListTemplate/meta/BU38BOQE.prototxt) | [A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis](https://openreview.net/forum?id=vVJZtlZB9D) | ICLR | 2023 | | | | | 1 | [abbr](/PaperListTemplate/meta/SP5UN1RF.prototxt) | [A Unified Framework for Soft Threshold Pruning](https://openreview.net/forum?id=cCFqcrq0d8) | ICLR | 2023 | | | | | 2 | [abbr](/PaperListTemplate/meta/Q3S45CWC.prototxt) | [Bit-Pruning: A Sparse Multiplication-Less Dot-Product](https://openreview.net/forum?id=YUDiZcZTI8) | ICLR | 2023 | | | | | 3 | [abbr](/PaperListTemplate/meta/JBRI286F.prototxt) | [CrAM: A Compression-Aware Minimizer](https://openreview.net/forum?id=_eTZBs-yedr) | ICLR | 2023 | | | | | 4 | [abbr](/PaperListTemplate/meta/22C0A4RH.prototxt) | [DFPC: Data flow driven pruning of coupled channels without data](https://openreview.net/forum?id=mhnHqRqcjYU) | ICLR | 2023 | | | | | 5 | [abbr](/PaperListTemplate/meta/TVCZSVZY.prototxt) | [DepthFL: Depthwise Federated Learning for Heterogeneous Clients](https://openreview.net/forum?id=pf8RIZTMU58) | ICLR | 2023 | | | | | 6 | [abbr](/PaperListTemplate/meta/ZHVKFNSL.prototxt) | [Diffusion Models for Causal Discovery via Topological Ordering](https://openreview.net/forum?id=Idusfje4-Wq) | ICLR | 2023 | | | | | 7 | [abbr](/PaperListTemplate/meta/9O673CMS.prototxt) | [Holistic Adversarially Robust Pruning](https://openreview.net/forum?id=sAJDi9lD06L) | ICLR | 2023 | | | | | 8 | [abbr](/PaperListTemplate/meta/Q0PKEEPI.prototxt) | [HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers](https://openreview.net/forum?id=D7srTrGhAs) | ICLR | 2023 | | | | | 9 | [abbr](/PaperListTemplate/meta/AZKA1WRH.prototxt) | [How I Learned to Stop Worrying and Love Retraining](https://openreview.net/forum?id=_nF5imFKQI) | ICLR | 2023 | | | | | 10 | [abbr](/PaperListTemplate/meta/RR92I0FK.prototxt) | [Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks](https://openreview.net/forum?id=4UldFtZ_CVF) | ICLR | 2023 | | | | | 11 | [abbr](/PaperListTemplate/meta/CSUM4GXD.prototxt) | [MECTA: Memory-Economic Continual Test-Time Model Adaptation](https://openreview.net/forum?id=N92hjSf5NNh) | ICLR | 2023 | | | | | 12 | [NTK-SAP](/PaperListTemplate/meta/HYTID4WD.prototxt) | [NTK-SAP: Improving neural network pruning by aligning training dynamics](https://openreview.net/forum?id=-5EWhW_4qWP) | ICLR | 2023 | | | | | 13 | [OTOv2](/PaperListTemplate/meta/QBBMHBHQ.prototxt) | [OTOv2: Automatic, Generic, User-Friendly](https://openreview.net/forum?id=7ynoX1ojPMt) | ICLR | 2023 | [Pytorch](https://github.com/tianyic/only_train_once) | | | | 14 | [abbr](/PaperListTemplate/meta/1EZ5JYL3.prototxt) | [Over-parameterized Model Optimization with Polyak-Lojasiewicz Condition](https://openreview.net/forum?id=aBIpZvMdS56) | ICLR | 2023 | | | | | 15 | [abbr](/PaperListTemplate/meta/4IT9WPPA.prototxt) | [Pruning Deep Neural Networks from a Sparsity Perspective](https://openreview.net/forum?id=i-DleYh34BM) | ICLR | 2023 | | | | | 16 | [abbr](/PaperListTemplate/meta/GEZARAUL.prototxt) | [Rethinking Graph Lottery Tickets: Graph Sparsity Matters](https://openreview.net/forum?id=fjh7UGQgOB) | ICLR | 2023 | | | | | 17 | [m](/PaperListTemplate/meta/0I1IQIH6.prototxt) | [Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph](https://openreview.net/forum?id=uVcDssQff) | ICLR | 2023 | | | | | 18 | [abbr](/PaperListTemplate/meta/DLHYYZU1.prototxt) | [Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective](https://openreview.net/forum?id=Dvs-a3aymPe) | ICLR | 2023 | | | | | 19 | [m](/PaperListTemplate/meta/RRGOXITB.prototxt) | [Symmetric Pruning in Quantum Neural Networks](https://openreview.net/forum?id=K96AogLDT2K) | ICLR | 2023 | | | | | 20 | [abbr](/PaperListTemplate/meta/MTKTZE3N.prototxt) | [TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning](https://openreview.net/forum?id=sZI1Oj9KBKy) | ICLR | 2023 | | | | | 21 | [m](/PaperListTemplate/meta/R4X91L5N.prototxt) | [Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?](https://openreview.net/forum?id=xSsW2Am-ukZ) | ICLR | 2023 | | | |

inst2

### author

Bingzhe Wu

Brian Chmiel

Dan Alistarh

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:---------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | 0 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

Daniel Soudry

Elias Frantar

| | meta | title | publication | year | code | note | cover | |---:|:---------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:--------------|-------:|:---------------------------------------------------|:---------------------------------------|:-----------------------------------------------------------------| | 0 | [SparseGPT](/PaperListTemplate/meta/sparsegpt.prototxt) | [SparseGPT: Massive Language Models Can be Accurately Pruned in one-shot.](https://arxiv.org/pdf/2301.00774.pdf) | arXiv | 2023 | [Pytorch](https://github.com/IST-DASLab/sparsegpt) | [note](/PaperListTemplate/notes/sparsegpt/SparseGPT.html) | |

Ivan Lazarevich

Name1

Name2

Nikita Malinin

Shiwei Liu

Song Han

Zhangyang Wang

Zhihang Yuan

References

https://github.com/he-y/Awesome-Pruning
https://github.com/htqin/awesome-model-quantization
https://github.com/csyhhu/Awesome-Deep-Neural-Network-Compression/tree/master
https://github.com/AojunZhou/Efficient-Deep-Learning
https://github.com/chester256/Model-Compression-Papers

PaperListTemplate

Paper List Template

Table of Contents

Getting Started

Paper List

References