Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation | Paper Citation Record

Observation dc40d292-4cf2-46ee-a940-4023f01d7983 · outbound

This paper cites Binarybert: Pushing the limit of bert quantization.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Binarybert: Pushing the limit of bert quantization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:57.667330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 829f914f-a6b3-4a26-93fe-7c48cd0be5c6 · outbound

This paper cites Federated fine-tuning of large language models under heterogeneous tasks and client resources.Advances in Neural Information Processing Systems, 37: 14457–14483, 2024.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Federated fine-tuning of large language models under heterogeneous tasks and client resources.Advances in Neural Information Processing Systems, 37: 14457–14483, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:57.727948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e5e4f8-3aa1-43f4-b374-c0775893f143 · outbound

This paper cites Ce-lora: Computation-efficient lora fine-tuning for language models.CoRR, 2025.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Ce-lora: Computation-efficient lora fine-tuning for language models.CoRR, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:57.789018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b10f8df-b062-44a4-b9db-5e73b59e7c13 · outbound

This paper cites LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:57.879086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa05aaa-d78d-4e87-abba-d1fb33ab20c8 · outbound

This paper cites Hessian-free optimization for learning deep multidimensional recurrent neural networks.Advances in Neural Information Processing Systems, 28, 2015.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Hessian-free optimization for learning deep multidimensional recurrent neural networks.Advances in Neural Information Processing Systems, 28, 2015

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.009389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347cdee2-d545-4bb6-abfe-ac372b75b811 · outbound

This paper cites Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.132349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e785c09b-20d2-4a6f-991d-29182f7982a0 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.253214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb65cf2-809b-434b-8327-d4561dd6a95a · outbound

This paper cites Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.419534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81998eaa-18f5-4c34-8de5-bfeb10e6d1a8 · outbound

This paper cites Predicting parameters in deep learning.Advances in neural information processing systems, 26, 2013.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Predicting parameters in deep learning.Advances in neural information processing systems, 26, 2013

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.539382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8593886f-bb44-4ff9-ae21-7058745dd726 · outbound

This paper cites Coreset-based neural network compression.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Coreset-based neural network compression

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.651587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4212534-6d08-43e8-ac53-500660fabe92 · outbound

This paper cites Reducing transformer depth on demand with structured dropout.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Reducing transformer depth on demand with structured dropout

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:58.815555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e5cb77-57db-4f56-aca9-a09d56084375 · outbound

This paper cites Depgraph: Towards any structural pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Depgraph: Towards any structural pruning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.010834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a553de21-3638-415d-a056-b6fac7f67c54 · outbound

This paper cites Geometric measure theory.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Geometric measure theory

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.232150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a998bcb7-ccb8-48c2-9103-5237a4d3ae33 · outbound

This paper cites Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.403201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8bfe133-019a-433d-af1d-5816d365fa01 · outbound

This paper cites Optimal brain compression: A framework for accurate post-training quantization and pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Optimal brain compression: A framework for accurate post-training quantization and pruning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.575040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c27ab0c7-20d9-419c-86f9-48c760c5a6bf · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.747709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38c1c143-6cce-43d0-8c2e-8905d447a0a7 · outbound

This paper cites The Llama 3 Herd of Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T13:30:59.893551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60746ec9-aa14-41a6-9c04-27fd519c4acb · outbound

This paper cites Reweighted Proximal Pruning for Large-Scale Language Representation.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Reweighted Proximal Pruning for Large-Scale Language Representation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.113570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8af465-7787-4c78-8712-2ac545802ffc · outbound

This paper cites Learning both weights and connections for efficient neural network.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Learning both weights and connections for efficient neural network

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.200249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd0a66d6-9342-4826-b44a-9505b07b4879 · outbound

This paper cites Flora: Low-rank adapters are secretly gradient compressors.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Flora: Low-rank adapters are secretly gradient compressors

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.267651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75b7bbc3-f206-4ec3-8529-8ba3ad957d01 · outbound

This paper cites Second order derivatives for network pruning: Optimal brain surgeon.Advances in neural information processing systems, 5, 1992.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Second order derivatives for network pruning: Optimal brain surgeon.Advances in neural information processing systems, 5, 1992

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.377084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b66a6d9-281c-4180-8916-7e5201e9d6fa · outbound

This paper cites Optimal brain surgeon and general network pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Optimal brain surgeon and general network pruning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.452127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea315db3-c540-4089-97b4-19033bee0107 · outbound

This paper cites Lora+ efficient low rank adaptation of large models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora+ efficient low rank adaptation of large models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.577372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0db7e1ab-1d6f-487a-ac22-a1175654dbad · outbound

This paper cites Subspace optimization for large language models with convergence guarantees.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Subspace optimization for large language models with convergence guarantees

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.636127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82da0f9e-fa4f-4c04-bde8-d07bdae9ff6c · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Measuring mathematical problem solving with the math dataset

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.720564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f34cec-dee5-4380-8315-9e35d55661e1 · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.770959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cfcee99-6076-4fd8-9bd8-e294b84fd331 · outbound

This paper cites Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.881626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d104d56-4bae-4022-8f64-9cf8a47b2b6d · outbound

This paper cites Accelerated sparse neural training: A provable and efficient method to find n: m transposable masks.Advancesin neural information processing systems, 34:21099–21111, 2021.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Accelerated sparse neural training: A provable and efficient method to find n: m transposable masks.Advancesin neural information processing systems, 34:21099–21111, 2021

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:00.993208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d7aa9df-d1ad-421d-93af-ead81aab9d49 · outbound

This paper cites A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.064826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9c9923-2138-4087-adf9-6dd6bf2f73b1 · outbound

This paper cites Some fundamental aspects about lipschitz continuity of neural networks.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Some fundamental aspects about lipschitz continuity of neural networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.163745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea43b0f6-c49e-4693-8e1d-6dfd56a352fa · outbound

This paper cites The optimal bert surgeon: Scalable and accurate second-order pruning for large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation The optimal bert surgeon: Scalable and accurate second-order pruning for large language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.261636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc589ecf-70d9-4690-90ee-b25976b1e18c · outbound

This paper cites Ziplm: Inference-aware structured pruning of language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Ziplm: Inference-aware structured pruning of language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.363823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd0e990b-98d0-4b0d-9226-683156e44756 · outbound

This paper cites Sparse fine-tuning for inference acceleration of large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Sparse fine-tuning for inference acceleration of large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.435804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa481466-fcc0-46aa-a3de-6c80f060e2d2 · outbound

This paper cites Albert: A lite bert for self-supervised learning of language representations.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Albert: A lite bert for self-supervised learning of language representations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.498965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd2b4232-c958-4914-99c0-78fd768a553c · outbound

This paper cites Lipschitz constant estimation of neural networks via sparse polynomial optimization.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lipschitz constant estimation of neural networks via sparse polynomial optimization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.572932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46224fc7-20ab-4d6d-93e2-2889a5679241 · outbound

This paper cites Optimal brain damage.Advances in neural information processing systems, 2, 1989.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Optimal brain damage.Advances in neural information processing systems, 2, 1989

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.644621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d5b2695-62ab-4310-b536-33e6b58d6be7 · outbound

This paper cites T\’yr-the-pruner: Unlocking accurate 50% structural pruning for llms via global sparsity distribution optimization.arXiv preprint arXiv:2503.09657, 2025.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation T\’yr-the-pruner: Unlocking accurate 50% structural pruning for llms via global sparsity distribution optimization.arXiv preprint arXiv:2503.09657, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.724813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f377ed9a-4110-41d9-9aa4-d46ba17cac09 · outbound

This paper cites Pruning filters for efficient convnets.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Pruning filters for efficient convnets

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.801639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fbccff-3515-48f2-a62c-8b650db8c896 · outbound

This paper cites SepPrune: Structured Pruning for Efficient Deep Speech Separation.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation SepPrune: Structured Pruning for Efficient Deep Speech Separation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:01.902086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02eaee91-d8c1-467b-ba31-d265e0f9b270 · outbound

This paper cites Memory-efficient llm training with online subspace descent.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Memory-efficient llm training with online subspace descent

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.028336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ce60b2-284a-4e14-b5cd-b0e312e95d29 · outbound

This paper cites Dynamic adaptation of lora fine-tuning for efficient and task-specific optimization of large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Dynamic adaptation of lora fine-tuning for efficient and task-specific optimization of large language models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.116020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee76c2c-d269-4488-b224-d10321023029 · outbound

This paper cites GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.244573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a19f575a-b0a2-4c96-8290-454a52ffdc12 · outbound

This paper cites Dora: Weight-decomposed low-rank adaptation.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Dora: Weight-decomposed low-rank adaptation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.321581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42116b73-24c9-4af0-889e-1b473d258b69 · outbound

This paper cites Ebert: Efficient bert inference with dynamic structured pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Ebert: Efficient bert inference with dynamic structured pruning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.406112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e949072-23a0-403c-b972-8d0394646aa3 · outbound

This paper cites Learning efficient convolutional networks through network slimming.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Learning efficient convolutional networks through network slimming

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.464210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1e7130-2b04-48c4-9699-0a982d3c7b13 · outbound

This paper cites Decoupled weight decay regularization.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Decoupled weight decay regularization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.512248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5852614b-c80a-48b6-af93-a3ccaf18e4df · outbound

This paper cites LCM-LoRA: A Universal Stable-Diffusion Acceleration Module.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.588362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04174519-2574-4dd5-9a98-aa8e09c27a20 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Llm-pruner: On the structural pruning of large language models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.664766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed1f517f-41bf-4dc7-8107-87eb88756a67 · outbound

This paper cites Pissa: Principal singular values and singular vectors adaptation of large language models.Advances in Neural Information Processing Systems, 37:121038–121072, 2024.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Pissa: Principal singular values and singular vectors adaptation of large language models.Advances in Neural Information Processing Systems, 37:121038–121072, 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.724189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 594ba95e-f619-4659-879d-f769ab4372e0 · outbound

This paper cites Pointer sentinel mixture models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Pointer sentinel mixture models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.773302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cecd9cf-dc79-41b9-aa5f-9e68b937cf78 · outbound

This paper cites Accelerating Sparse Deep Neural Networks.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Accelerating Sparse Deep Neural Networks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.854535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b116ae71-3485-4aba-b171-d45906e821dd · outbound

This paper cites Pruning convolutional neural networks for resource efficient inference.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Pruning convolutional neural networks for resource efficient inference

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.913442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 628ae958-cc78-481d-8b24-d10852a51e77 · outbound

This paper cites Importance estimation for neural network pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Importance estimation for neural network pruning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:02.966630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb9fdb9-f12a-4cb4-9ffe-f53d0ad78993 · outbound

This paper cites Sosp: Efficiently capturing global correlations by second-order structured pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Sosp: Efficiently capturing global correlations by second-order structured pruning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.016361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78eb8584-3cdc-4233-a5dc-9230d16c2916 · outbound

This paper cites Gradient-free structured pruning with unlabeled data.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Gradient-free structured pruning with unlabeled data

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.069053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d9d37ea-f880-4ce3-8101-013c7a10833a · outbound

This paper cites Meta-kd: A meta knowledge distillation framework for language model compression across domains.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Meta-kd: A meta knowledge distillation framework for language model compression across domains

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.120217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4eaa6c2-9814-4e3c-a220-a47cafac1877 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.178876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 151baf2e-ef0a-48ff-8549-056c48550fa5 · outbound

This paper cites Structural pruning via latency-saliency knapsack.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Structural pruning via latency-saliency knapsack

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.252672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a898b301-55d1-458a-b5c6-098fa3d90597 · outbound

This paper cites Parameter Efficient Reinforcement Learning from Human Feedback.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Parameter Efficient Reinforcement Learning from Human Feedback

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.312654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e895c56-e7f8-4dd0-9ba5-5b4538ecc5ce · outbound

This paper cites Woodfisher: Efficient second-order approximation for neural network compression.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Woodfisher: Efficient second-order approximation for neural network compression

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.388666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeaff8f7-a551-48ec-a25b-1818c93bbbf2 · outbound

This paper cites A simple and effective pruning approach for large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation A simple and effective pruning approach for large language models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.449666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b80c776c-8e10-4a80-8266-6ea6aa176c55 · outbound

This paper cites Patient knowledge distillation for bert model compression.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Patient knowledge distillation for bert model compression

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.499646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9768038-dcf6-4def-bb72-9a0c0cf783a8 · outbound

This paper cites Contrastive distillation on intermediate representations for language model compression.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Contrastive distillation on intermediate representations for language model compression

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.582653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698325b9-6deb-43ea-8a43-ad4849f0bff1 · outbound

This paper cites Improving LoRA in Privacy-preserving Federated Learning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Improving LoRA in Privacy-preserving Federated Learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.641942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aaf5e46-c21b-4668-9174-283dad6bbc6a · outbound

This paper cites Mobilebert: a compact task-agnostic bert for resource-limited devices.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Mobilebert: a compact task-agnostic bert for resource-limited devices

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.690169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f06c780-054b-4572-b047-7384f857302a · outbound

This paper cites DarwinLM: Evolutionary Structured Pruning of Large Language Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation DarwinLM: Evolutionary Structured Pruning of Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.739460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0216e233-01c7-4c2e-89a7-237199be87e7 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation LLaMA: Open and Efficient Foundation Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.822129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a2da0b-79bc-48d7-9642-64b67cd3d4bd · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.870042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921b7e6b-9ba1-4951-89f4-9ebaf443aaa5 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.928668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b8fa66-7df6-4169-98db-b4ada96729d5 · outbound

This paper cites Glue: A multi-task benchmark and analysis platform for natural language understanding.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Glue: A multi-task benchmark and analysis platform for natural language understanding

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:03.986729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f842fe44-9d50-4586-9b46-808aa377678d · outbound

This paper cites Lora-ga: Low-rank adaptation with gradient approximation.Advances in Neural Information Processing Systems, 37:54905–54931, 2024.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora-ga: Low-rank adaptation with gradient approximation.Advances in Neural Information Processing Systems, 37:54905–54931, 2024

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.026847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b914099e-0017-4294-b5d7-c0e39b07384a · outbound

This paper cites Lora-pro: Are low-rank adapters properly optimized? In The Thirteenth International Conference on Learning Representations, 2024.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora-pro: Are low-rank adapters properly optimized? In The Thirteenth International Conference on Learning Representations, 2024

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.133041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1487b643-c4e3-42b9-9ef9-b4087d23ba37 · outbound

This paper cites Assessing the brittleness of safety alignment via pruning and low-rank modifications.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Assessing the brittleness of safety alignment via pruning and low-rank modifications

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.196398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0984fd7f-d6e7-4b3d-8e53-868410bd99d6 · outbound

This paper cites Structured optimal brain pruning for large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Structured optimal brain pruning for large language models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.272275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54288fbb-9f33-44eb-bda4-7ad7a22ba123 · outbound

This paper cites The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information.Advances in Neural Information Processing Systems, 37:139621–139649, 2024.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information.Advances in Neural Information Processing Systems, 37:139621–139649, 2024

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.340595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9aa7571-1b63-427b-9019-1ca5061b3c0b · outbound

This paper cites Structured pruning learns compact and accurate models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Structured pruning learns compact and accurate models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.422456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004f3f9e-bb2a-4b06-bc39-57ed81f83761 · outbound

This paper cites MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.500933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4e1ad9-f87e-4464-adfd-1e93b5909e6b · outbound

This paper cites Deebert: Dynamic early exiting for accelerating bert inference.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Deebert: Dynamic early exiting for accelerating bert inference

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.514773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c20982d-41d1-4529-98da-8cc4468b79c7 · outbound

This paper cites Rethinking network pruning–under the pre-train and fine-tune paradigm.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Rethinking network pruning–under the pre-train and fine-tune paradigm

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.600548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c72107-9900-4c67-93a8-b16ccdd102bf · outbound

This paper cites Theoretical characterization of how neural network pruning affects its generalization.OpenReview, 2023.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Theoretical characterization of how neural network pruning affects its generalization.OpenReview, 2023

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.693547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 310b74ce-55c8-4d1a-b4c6-717d9304bea0 · outbound

This paper cites Mtl-lora: Low-rank adaptation for multi-task learning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Mtl-lora: Low-rank adaptation for multi-task learning

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.788138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c78340-18b5-47cd-8366-53db9232320f · outbound

This paper cites Wanda++: Pruning large language models via regional gradients.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Wanda++: Pruning large language models via regional gradients

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.870527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede60751-dd98-42db-9867-a69701b04380 · outbound

This paper cites Gradient-based intra-attention pruning on pre-trained language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Gradient-based intra-attention pruning on pre-trained language models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.951471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff35142-5fa4-4932-9f00-d9b61fffd795 · outbound

This paper cites Zeroquant: Efficient and affordable post-training quantization for large-scale transformers.Advances in neural information processing systems, 35:27168–27183, 2022.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Zeroquant: Efficient and affordable post-training quantization for large-scale transformers.Advances in neural information processing systems, 35:27168–27183, 2022

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:04.990337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5541c67e-4196-4196-b9d8-c229384ac352 · outbound

This paper cites Lora done rite: Robust invariant transformation equilibration for lora optimization.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora done rite: Robust invariant transformation equilibration for lora optimization

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.051943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e77a342-d52c-4a35-92c5-13246ca3e522 · outbound

This paper cites Metamath: Bootstrap your own mathematical questions for large language models.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Metamath: Bootstrap your own mathematical questions for large language models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.165928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50972c07-37a0-4a48-94c9-1c93fd4060dc · outbound

This paper cites Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.241541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e775b1-f0b2-40cb-aa5c-af2c90e37031 · outbound

This paper cites Altlora: Towards better gradient approximation in low-rank adaptation with alternating projections.arXiv preprint arXiv:2505.12455, 2025.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Altlora: Towards better gradient approximation in low-rank adaptation with alternating projections.arXiv preprint arXiv:2505.12455, 2025

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.348090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17a03dc-21e9-4c78-a211-0c9296c0c804 · outbound

This paper cites Q8bert: Quantized 8bit bert.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Q8bert: Quantized 8bit bert

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.494508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ff9d6a-c44d-496f-80fd-7ddb175e5aec · outbound

This paper cites Block-diagonal Hessian-free Optimization for Training Neural Networks.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Block-diagonal Hessian-free Optimization for Training Neural Networks

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.703639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a1f2bc-20fc-45e9-8af4-1adcf7e87a18 · outbound

This paper cites Loraprune: Struc- tured pruning meets low-rank parameter-efficient fine-tuning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Loraprune: Struc- tured pruning meets low-rank parameter-efficient fine-tuning

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:05.792586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2d8d4ed-11ae-45ac-8387-58b1465c45bf · outbound

This paper cites Adap- tive budget allocation for parameter-efficient fine-tuning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Adap- tive budget allocation for parameter-efficient fine-tuning

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:06.001832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684e44fd-643e-43a4-9cf3-f192963eacdb · outbound

This paper cites Lora-one: One-step full gradient could suffice for fine-tuning large language models, provably and efficiently.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Lora-one: One-step full gradient could suffice for fine-tuning large language models, provably and efficiently

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:06.136237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58561001-168f-4cb2-968d-059b871e41c0 · outbound

This paper cites Galore: Memory-efficient llm training by gradient low-rank projection.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Galore: Memory-efficient llm training by gradient low-rank projection

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:06.262731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ef3e90-57fa-4ee7-bd45-c9a061a9e25f · outbound

This paper cites Adaptive Activation-based Structured Pruning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Adaptive Activation-based Structured Pruning

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:06.404589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db05630d-57f8-4472-8431-ac7392949e70 · outbound

This paper cites Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T13:31:06.541083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41485d92-3dbb-484b-bc63-31ad17e3a477 · outbound

This paper cites To prune, or not to prune: exploring the efficacy of pruning for model compression.

Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation To prune, or not to prune: exploring the efficacy of pruning for model compression

Reference 97

Resolution: malformed identifier; no resolver link, observed 2026-08-04T13:31:06.702424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers