Pith. sign in

Paper Citation Record · LEDGER

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

As of 18 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 1 inbound Pith citation observation for arXiv:2509.25136.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.25136 v3

Coverage vector

measured 61 of 61 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:49:04.152064Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-10T01:58:58.772489Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T02:06:42.178030Z

Reference resolution

61 of 61 outbound references displayed

  • verified exact6
  • verified fuzzy25
  • unresolved30
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe2e7ea3-762f-43fc-a53c-2414fc48a8e8 · outbound

This paper cites write newline.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.928600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.928600Z digest=sha256:bfbe06d557fd550f58532b1034f10ebaae042d520e590e1e4cf7b7c263e23b43

Observation 2fc55f4c-d5fd-4e4c-b162-1c7e880ea7fd · outbound

This paper cites Compressing pre-trained language models by matrix decomposition.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Compressing pre-trained language models by matrix decomposition

Reference 2

Resolution
verified exact
doi, observed 2026-08-15T15:49:04.210277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.933765Z digest=sha256:1202d8d6e69aa3909e709e1387cba039e37a6069c9e6e17dcc85de28fb1ccb07

Observation f9c131ce-a910-48ab-9d8e-f5cb3bf61bd9 · outbound

This paper cites High Performance Convolutional Neural Networks for Document Processing.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression High Performance Convolutional Neural Networks for Document Processing

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.870497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.937901Z digest=sha256:25e1c5203cc6a889657fe52476abbe961b199fc958d65759b9ae4c0124fffb84

Observation d56d511c-b2b5-4be4-86d4-be0e2f1a0491 · outbound

This paper cites Drone: Data-aware low-rank compression for large nlp models.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Drone: Data-aware low-rank compression for large nlp models

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.860554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.941909Z digest=sha256:42ed0c65a8338bb9decc8d2b428312244e4cae48ffca838bf4386b6deb799790

Observation 8808a307-e82d-48fe-aa3a-d750e668fec3 · outbound

This paper cites Going beyond neural network feature similarity: The network feature complexity and its interpretation using category theory.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Going beyond neural network feature similarity: The network feature complexity and its interpretation using category theory

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.850699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.945595Z digest=sha256:0ed7e0badb5cbcdbee7ec60c3929a8173ca32e58cc218bc5c3e155f74da627dd

Observation 29c6ec3a-7a9f-450f-88b3-6e4b7c7d9b80 · outbound

This paper cites Parseval networks: improving robustness to adversarial examples.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Parseval networks: improving robustness to adversarial examples

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.840380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.949128Z digest=sha256:b744249032a95af883cf9d8aca2e2e715e6cef0351b5c9100c650c3ca744e8eb

Observation 5bc3edd0-ece9-4684-8b8c-519382e01984 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Imagenet: A large-scale hierarchical image database

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.952984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.952984Z digest=sha256:8606b8f2dd113de4778ac92882ec69ebf38626e66a79625f25ed03b0e7222cd1

Observation cc9d3ded-8af2-4ce1-a80c-205a4175ce7c · outbound

This paper cites Exploiting linear structure within convolutional networks for efficient evaluation.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Exploiting linear structure within convolutional networks for efficient evaluation

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.830180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.956983Z digest=sha256:6a8eaaf2174767bc4b18f9620bb4e20ecc99269a18197ce47ee758ab4363c72e

Observation 7181fc49-396d-49c2-8763-ad385ad417ad · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression An image is worth 16x16 words: Transformers for image recognition at scale

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.960705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.960705Z digest=sha256:b9e99fcada554fefc1159bc19f37d69a7a556ac98b0df47cb8bf93bc81a1054a

Observation 91335a01-b9ac-47c2-8217-952397b7f242 · outbound

This paper cites Pulp: A linear programming toolkit for python.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Pulp: A linear programming toolkit for python

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.813291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.964618Z digest=sha256:661d6511a7af6e8b0afdeca4a878527caad55bf3da9b51cc12b9565d586dbf0b

Observation 2a061e1b-77d5-47b1-b384-744b0fffea32 · outbound

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

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Optimal brain compression: A framework for accurate post-training quantization and pruning

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.802799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.968185Z digest=sha256:382d86f876c2d9e3ac4f0194e7719f3afbcf42215459811a4df5cd3d4b14866a

Observation 0ccb5981-f0e9-4d16-b86c-cf5068ab7665 · outbound

This paper cites OPTQ : Accurate quantization for generative pre-trained transformers.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression OPTQ : Accurate quantization for generative pre-trained transformers

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.971794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.971794Z digest=sha256:872ea7ea7d39b9fba6a48c33a1d0b2d0bd3f7d0ad268dbdaf4cecf8d2bb9aaa5

Observation 377532e5-f173-4d91-9340-c74db335cf6a · outbound

This paper cites A Survey of Quantization Methods for Efficient Neural Network Inference.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression A Survey of Quantization Methods for Efficient Neural Network Inference

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.975378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.975378Z digest=sha256:f699624254a81a9169c0b5f57b5341ca5f0fb3745666e5fab690eb48fe9b9d37

Observation 102ab468-a9a8-42ed-a1bf-bdc3137966c3 · outbound

This paper cites Golub and C.F.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Golub and C.F

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.784577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.979326Z digest=sha256:9e3a130b24bbfa0a88432da4009a409d1cbafe788a0483196bde1dae8d71aa61

Observation 6707cdab-62ae-483a-b94e-8fa093494b9c · outbound

This paper cites Feature variance ratio-guided channel pruning for deep convolutional network acceleration.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Feature variance ratio-guided channel pruning for deep convolutional network acceleration

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.773089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:03.982731Z digest=sha256:d819d135293a8a31830d9346b4d3b35b9ccc8fe0f5d884b67719d6d71b1bdbbf

Observation 2e1c32e4-afae-4556-bfd4-d211fde01b2b · outbound

This paper cites Deep Residual Learning for Image Recognition.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Deep Residual Learning for Image Recognition

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.986211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.986211Z digest=sha256:c113682e9fb53ca98455e0ef58ff99fede7902e92b44c55216e620b147a6b6ba

Observation aa997362-ee34-4eac-a01c-0a7154539700 · outbound

This paper cites Benchmarking neural network robustness to common corruptions and perturbations.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Benchmarking neural network robustness to common corruptions and perturbations

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.989920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.989920Z digest=sha256:ac7fb8a04e6ffb208297b9fcf1ebed700aaffe31748a48a7629e355dbfc24856

Observation 228c4d07-9e6e-48c5-bbfb-cae58b28aa43 · outbound

This paper cites Gaussian Error Linear Units (GELUs).

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Gaussian Error Linear Units (GELUs)

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.993342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.993342Z digest=sha256:eb91d973c0029a68d6c37ee293ddbc07268ccab82670bc7727d79c2b255e0e27

Observation 7520e77a-b5b8-4892-b780-bc6d7a8ce3d2 · outbound

This paper cites Magma: Enabling exascale performance with accelerated blas and lapack for diverse gpu architectures.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Magma: Enabling exascale performance with accelerated blas and lapack for diverse gpu architectures

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:03.996982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:03.996982Z digest=sha256:559b56e3afd3184acdc29706b12c48cbaecac70c305db2081ac262a525ab9d64

Observation b5e4a6ee-58da-40db-940d-3461cfb311b0 · outbound

This paper cites Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.754945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.000785Z digest=sha256:1899286a8abba946f7a1bc3e56d5fc1feb1299679225078158495f05bae7b55c

Observation c13337cc-0b3d-402a-a0c2-be8a5ed53986 · outbound

This paper cites Dynamic low-rank estimation for transformer-based language models.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Dynamic low-rank estimation for transformer-based language models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.004381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.004381Z digest=sha256:62094da69dbf08d2b4e71b7b9d40a626f3718fa1e1b01ca5b2a8399035c61170

Observation a1c3e520-aa03-4321-a39f-9f955e479e6d · outbound

This paper cites Carreira-Perpiñán.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Carreira-Perpiñán

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.008587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.008587Z digest=sha256:64476fbfbbf646c9a12b62a0e335690250f38b73d346d962455a5047df1c8824

Observation 8cd9cc59-719d-4293-80f2-66213ca377de · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Batch normalization: Accelerating deep network training by reducing internal covariate shift

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.743462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.012118Z digest=sha256:ebf73478340c50d7b73a996448957fb22ab5c328b288284641b0182540bc26ea

Observation b5071d2e-d931-440d-bfb9-5e74e2010f93 · outbound

This paper cites Quantization and training of neural networks for efficient integer-arithmetic-only inference.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Quantization and training of neural networks for efficient integer-arithmetic-only inference

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.015772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.015772Z digest=sha256:a86142e457a61e3f9268b8c5d5636111705a919193cbc8a2c7e3fa8489ad6369

Observation 94cb8a45-5d3e-40c5-9c10-eff060f8f333 · outbound

This paper cites Speeding up Convolutional Neural Networks with Low Rank Expansions.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Speeding up Convolutional Neural Networks with Low Rank Expansions

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.019418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.019418Z digest=sha256:757b1a4db47089908f061ead6145065768a6e247eff822b5375afec907cb8521

Observation d5802005-55d9-44b0-a4f6-ff6fd1281097 · outbound

This paper cites Stability analysis of fluid flows using Lagrangian Perturbation Theory (LPT): application to the plane Couette flow.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Stability analysis of fluid flows using Lagrangian Perturbation Theory (LPT): application to the plane Couette flow

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.023545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.023545Z digest=sha256:03958c9c0f61ca1af13f020c76b85ec29b4be67c45b767a7655c03e256d59bb1

Observation 5b016559-9600-4d90-aa69-efa73b3d40be · outbound

This paper cites Learning multiple layers of features from tiny images.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Learning multiple layers of features from tiny images

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.028605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.028605Z digest=sha256:f28932b6df61d7b898da702c33c5cba5df68353cae1c37872a3bb3b341819734

Observation 58fb2594-8b31-453f-b51d-1f6e388d294f · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Imagenet classification with deep convolutional neural networks

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.032810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.032810Z digest=sha256:6e21f325402f93dcba103d6e3b489067be402c9d53929399164e1fdcbf63d0f0

Observation a5cd88b4-b3b0-4c1f-8867-fd3af79284d2 · outbound

This paper cites Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.036338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.036338Z digest=sha256:599cab4ab0a6a02145cac3e10215460bcca028beb446569b4cbb15ee5fbbde2a

Observation ffc68eca-a2b6-4f00-8148-2420352c7cdf · outbound

This paper cites Deep learning.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Deep learning

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.040215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.040215Z digest=sha256:cfee2f4aaf4117f271d233892f6d36377a3a2d3619f5a68ac23341b9c445a8e4

Observation 98671b65-f957-43ba-b178-98070c9b4e6b · outbound

This paper cites Training-Free Restoration of Pruned Neural Networks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Training-Free Restoration of Pruned Neural Networks

Reference 31

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:49:04.339398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.044217Z digest=sha256:bf1eea02f2a6f3f7ee2ec8edb4291b09d1f2a59701d0ab2373625dd964312052

Observation 7eb8b110-2ce3-47a0-970f-e41b101fc45e · outbound

This paper cites Compressing neural networks: Towards determining the optimal layer-wise decomposition.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Compressing neural networks: Towards determining the optimal layer-wise decomposition

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.711751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.048035Z digest=sha256:dce4b4096c9f11e55b8696c914732d92222d8e2d038cd9899a668565b076ba2f

Observation fd78d61a-5d7d-434c-b380-0ce48452ee50 · outbound

This paper cites TorchVision: PyTorch's Computer Vision library , November 2016.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression TorchVision: PyTorch's Computer Vision library , November 2016

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.699996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.051386Z digest=sha256:5ddd6aa96123849fcd0d43ce7f1bafff84d2a7206546c0963aef19638fea1812

Observation 54221432-d83a-4208-9b08-ca7cb6479cfb · outbound

This paper cites TVSP rune - pruning non-discriminative filters via total variation separability of intermediate representations without fine tuning.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression TVSP rune - pruning non-discriminative filters via total variation separability of intermediate representations without fine tuning

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.688877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.054650Z digest=sha256:09952ffaadac02d4a14a431846d25bdd653605a97325e9c60fcd560cc16f602a

Observation b36fe078-ef65-47c1-87e0-1033ffdfacba · outbound

This paper cites an unresolved cited work.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-15T15:49:04.677966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.058164Z digest=sha256:f5dc10d4f07c1cefff6ac9b1e0d63386e9b2c25c6bcd1ca9772f493dc66d885e

Observation 9f20007c-d464-4296-9da5-97801d2cd56f · outbound

This paper cites DFPC : Data flow driven pruning of coupled channels without data.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression DFPC : Data flow driven pruning of coupled channels without data

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.667411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.062083Z digest=sha256:5bdc2474070ba0aa53971d33d725c710fdaae4606547e470bf303979d099d3fa

Observation 1db16b67-2e87-4cd0-aecc-2f7bf27453b9 · outbound

This paper cites cuSOLVER Library.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression cuSOLVER Library

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.657005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.065490Z digest=sha256:09651147e4c7a66d5133e9641cd3a26e3af110c6f7b4d010a2cb2508dbf2fdd1

Observation 174f5154-bd14-424d-8045-fca68e2018b9 · outbound

This paper cites PyTorch: an imperative style, high-performance deep learning library.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression PyTorch: an imperative style, high-performance deep learning library

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.068770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.068770Z digest=sha256:bbfa9b0aed73748aeca5982583e7345eabb329cc24b4ee2a877eac945b0b59e1

Observation 5b7b5532-114d-495f-9ce7-70ff00217c09 · outbound

This paper cites Stable low-rank tensor decomposition for compression of convolutional neural network.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Stable low-rank tensor decomposition for compression of convolutional neural network

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.639171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.072086Z digest=sha256:f1f50bcabdb51db85a27486241ac3dc705957affa4afab26abe44a56f1da4995

Observation eab9afba-3b37-4eb1-95bf-a662cb537022 · outbound

This paper cites Dobi- SVD : Differentiable SVD for LLM compression and some new perspectives.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Dobi- SVD : Differentiable SVD for LLM compression and some new perspectives

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.628362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.075415Z digest=sha256:d372fe1588145fba3672c4aaa91403aef0a4b5e9647efd04c9219967783e8def

Observation a933febd-2a85-4693-b2c0-7ce847ae25a0 · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Mobilenetv2: Inverted residuals and linear bottlenecks

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.618019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.078658Z digest=sha256:b3017e4aaeea9323c0fa3074c5a21ae01995c4c5cf4103af83f2009349f0da9b

Observation cdffc05f-97f8-4d48-9fa5-6723ddd603b1 · outbound

This paper cites On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization

Reference 42

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:49:04.324667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.081895Z digest=sha256:10cc3f48e41b4745367c9bc9406cd1f7a0e675e96cc7f999e9bea732dbc887c9

Observation baef1aaf-7fd2-4d64-a9df-d91db3a1d46b · outbound

This paper cites ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.085434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.085434Z digest=sha256:ce9ea7b53f750cc4cf5f5cfe9f0ba15ca145e3ef3114b969ce4d9c397b3ccbc2

Observation a64a3a6a-8d61-420a-9bb8-8cf066c43d55 · outbound

This paper cites Solution methods for the multiple-choice knapsack problem and their applications.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Solution methods for the multiple-choice knapsack problem and their applications

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.090214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.090214Z digest=sha256:6fc3365f44d36e8f45e3110ae456af4cccdedf7d3ce2b80cdd3c7d328f7374a5

Observation 546681fd-38ca-4290-a9f1-679f690949f0 · outbound

This paper cites Training data-efficient image transformers &; distillation through attention.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Training data-efficient image transformers &; distillation through attention

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.607002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.093781Z digest=sha256:8747742ceb6e40f63441d27e665cb17e4e64585d90567f803fc3074f6f04fe27

Observation e4061699-89ee-4f90-ab6e-005fe92980f2 · outbound

This paper cites Attention is all you need.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Attention is all you need

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.097083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.097083Z digest=sha256:61a4999a6141b87ce9df859091c9c0a74faead418db02d6ced21edfb56f85e10

Observation 999ad730-a69b-4764-9fa5-2cbdf544edbe · outbound

This paper cites Forget the data and fine-tuning! just fold the network to compress.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Forget the data and fine-tuning! just fold the network to compress

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.588324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.100401Z digest=sha256:53ce1014e0d6e30a152f690cbad04f371950b6d11f686a1bad92a77bb89e59b4

Observation 3736fbce-13c2-45da-9620-009cfd283fc2 · outbound

This paper cites Practical Network Acceleration with Tiny Sets.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Practical Network Acceleration with Tiny Sets

Reference 48

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:49:04.298797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.103854Z digest=sha256:e8652560ac813dfbd0c3bf9bdc19c7f463fbb46106c7c64aa72564aa51dfaf27

Observation 07db194d-6bc8-4dab-9d37-46b3bb80951b · outbound

This paper cites SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.107497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.107497Z digest=sha256:c5b6ead03adf94f77d8376e1493910bac954966beaf50de72e8590bddc968e30

Observation 7c4b51f2-c04d-41b2-a923-2df7e9fc6a9b · outbound

This paper cites SVD - LLM : Truncation-aware singular value decomposition for large language model compression.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression SVD - LLM : Truncation-aware singular value decomposition for large language model compression

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.577896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.111231Z digest=sha256:ffba4e81c730f4b2b7d35288ae36299b4c7dec6c34e0f4a878f400d8fd09d1bc

Observation 02106b97-027b-4b1a-a560-e2b2bd1cba44 · outbound

This paper cites PyTorch Image Models.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression PyTorch Image Models

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.567429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.114729Z digest=sha256:96920ae41fa7487d1b42fb8fd620f81ab62ab0c66af3daa682411a764d596d99

Observation 9b3d494e-345c-41ee-b612-eead56b3c17a · outbound

This paper cites Aggregated Residual Transformations for Deep Neural Networks.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Aggregated Residual Transformations for Deep Neural Networks

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.118576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.118576Z digest=sha256:841f93676cbedfd098fdb7e7a06c65bd7321a857a0160ae27a6acaa7d6e2b30b

Observation b2991234-7152-4221-8f14-115f10bb289c · outbound

This paper cites GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

Reference 53

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:49:04.262284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.122201Z digest=sha256:dc0254592f9e882ca653d8f1761aa3c56bc501ce45a9f0db71c17d6af2c876f0

Observation 6460fabf-f7a7-4a88-b17a-d959a4f24d71 · outbound

This paper cites Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.125653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.125653Z digest=sha256:d0ffcb4a2b36834297c6b79360dd7219faad304bf59e58ea0890e35902ac90c0

Observation db82b387-d690-4f92-9008-da2dbf2f6b62 · outbound

This paper cites Towards efficient tensor decomposition-based dnn model compression with optimization framework.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Towards efficient tensor decomposition-based dnn model compression with optimization framework

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.556474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.129172Z digest=sha256:187e1745bbd39305c8884ad5d022c957864825510e62ab31d014c524a9587b07

Observation c83115bd-8108-44ed-b30b-01ea02a7f313 · outbound

This paper cites SVD-NAS: Coupling Low-Rank Approximation and Neural Architecture Search.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression SVD-NAS: Coupling Low-Rank Approximation and Neural Architecture Search

Reference 56

Resolution
verified exact
local_arxiv, observed 2026-08-15T15:49:04.236254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.132605Z digest=sha256:73ffe46cf664ae82cd5ca9876fd7a6e88735984138c9efbfb3e958698db915a1

Observation ca20398e-34b0-4520-8529-c4e83b9b1336 · outbound

This paper cites ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.136343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.136343Z digest=sha256:5114305732342494c20634043a402fb7bce371688f03d7eca5901a981a5bbe8e

Observation 590e6733-baf2-4f4f-b120-ca069db05d96 · outbound

This paper cites Dense vision transformer compression with few samples.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Dense vision transformer compression with few samples

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:49:04.545206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-15T15:49:04.141076Z digest=sha256:f6d9f330804b68508b1fc9d3904294a5851b9740b9bf0622bbdf6953b501736c

Observation 25b5ce01-85e1-42f0-9b3f-53be7ba49106 · outbound

This paper cites @esa (Ref.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression @esa (Ref

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.144364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.144364Z digest=sha256:79c4294426b258dff81006a3dbce6b763cec70134d8e0e0b9af0e5177c25b76c

Observation 4511ebc0-42ce-4e72-b556-67a0b57f397a · outbound

This paper cites an unresolved cited work.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Unresolved cited work

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.148354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.148354Z digest=sha256:f72cdedd4f708039cc75f559f88e53e611069d58801798e3197c8f3134483079

Observation 62deaeb2-be17-4881-b396-98e7d1df57af · outbound

This paper cites an unresolved cited work.

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Unresolved cited work

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-15T15:49:04.152064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:49:04.152064Z digest=sha256:68e50fb96f92901d755d32bfbd07d1069a9a3e9780d4baae05f96e78e3434021

Pith citing papers

Observation a178c83e-c38f-441c-b43e-3f28b0643cbc · inbound

SLORR: Simple and Efficient In-Training Low-Rank Regularization cites this paper.

SLORR: Simple and Efficient In-Training Low-Rank Regularization BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

Reference 60

Resolution
verified exact
local_arxiv, observed 2026-07-10T02:06:42.179511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-07-10T01:58:58.772489Z digest=sha256:7b96980c97d09cd6453b6837f22002c1b08a697460acfae4c5d831532726b406