Paper Citation Record · LEDGER

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

As of 10 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 7 inbound Pith citation observations for arXiv:2502.01235.

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

pith.paper-citation-record.v1
2502.01235 v3

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T16:14:03.217184Z

measured 74 of 74 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:26:48.286017Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T08:19:44.419278Z

Reference resolution

67 of 67 outbound references displayed

verified exact0
verified fuzzy43
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 462bf1e5-8550-47be-9f93-7e2ff097b7f0 · outbound

This paper cites write newline.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.888781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 644056ed-832b-441d-ab4b-bdeec8ef356a · outbound

This paper cites B., and Misiakiewicz, T.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently B., and Misiakiewicz, T

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.114840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e6ba61ca-11b8-4775-9bff-8f07af338dcc · outbound

This paper cites B., Gheissari, R., and Jagannath, A.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently B., Gheissari, R., and Jagannath, A

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.105638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 626bc842-4736-4de2-bc3c-d861dc6a84d4 · outbound

This paper cites A., Suzuki, T., Wang, Z., Wu, D., and Yang, G.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A., Suzuki, T., Wang, Z., Wu, D., and Yang, G

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.096306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7c5dcf07-7fc7-437a-93a3-ce4d5ed23f94 · outbound

This paper cites On Learning Gaussian Multi-index Models with Gradient Flow.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently On Learning Gaussian Multi-index Models with Gradient Flow

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.905499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f1f1f3c-05de-4915-b892-5865ddb6579d · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.085936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d4b68798-acee-4590-a631-7ca4376979fc · outbound

This paper cites and Globerson, A.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently and Globerson, A

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.075394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 85cc30b3-8bac-4898-8ece-af56d093965d · outbound

This paper cites Evaluating Large Language Models Trained on Code.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Evaluating Large Language Models Trained on Code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.916927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48546637-5ae7-47bd-806c-e3c3b1d91fc1 · outbound

This paper cites Spectral Methods for Data Science: A Statistical Perspective.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Spectral Methods for Data Science: A Statistical Perspective

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.065085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 649b22e3-415b-452e-a306-84835fc35e7b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.923917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e462e18-0f7e-4044-a8b6-8b0dab09db04 · outbound

This paper cites Asymptotics of feature learning in two-layer networks after one gradient-step.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Asymptotics of feature learning in two-layer networks after one gradient-step

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.055044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e116cae6-7729-44d1-8a60-493faa78a7d5 · outbound

This paper cites Neural Networks can Learn Representations with Gradient Descent.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Neural Networks can Learn Representations with Gradient Descent

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.045696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3314f5aa-ff33-4535-a474-0267a9f8058e · outbound

This paper cites A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.036566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf0b7bf0-f1c0-48d5-acaf-4b6dc09c3b45 · outbound

This paper cites Gradient dynamics for low-rank fine-tuning beyond kernels.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Gradient dynamics for low-rank fine-tuning beyond kernels

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.937714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e1709bc-9387-456d-b21a-7b1c45bb00f9 · outbound

This paper cites A Validation Approach to Over-parameterized Matrix and Image Recovery.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Validation Approach to Over-parameterized Matrix and Image Recovery

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.941442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b99e2f76-42ae-4e11-924f-b3f4a8c76130 · outbound

This paper cites Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.944915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8382eb65-8cfe-40cf-94e2-891b6f27ced0 · outbound

This paper cites Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.948587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23b7d1fe-500e-4e8d-88e6-7e3fcfb18958 · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:04.027191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 74c1a6d8-fd61-410d-bcfe-7ba3be3cef3a · outbound

This paper cites LoRA+: Efficient Low Rank Adaptation of Large Models.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently LoRA+: Efficient Low Rank Adaptation of Large Models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.018721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c48f2021-df4d-44a0-b273-6e436e1f82f2 · outbound

This paper cites Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.009812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 413f5f18-1fbf-4421-9384-0a51ac54e442 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Measuring Massive Multitask Language Understanding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:04.000570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37da9ef0-368b-45d1-bc2a-5327a1357c34 · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.989655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86570e6e-43f2-482e-b0b5-2d0bf88405bb · outbound

This paper cites Parameter-Efficient Transfer Learning for NLP.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Parameter-Efficient Transfer Learning for NLP

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.979644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ec156b75-6e4e-4e6c-a419-f6c25f90b649 · outbound

This paper cites J., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently J., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.967917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f9d3f4ab-d812-4bee-90cb-53184eb670d1 · outbound

This paper cites Neural Tangent Kernel: Convergence and Generalization in Neural Networks.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Neural Tangent Kernel: Convergence and Generalization in Neural Networks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.815353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 74993bcd-6c05-4561-911d-fcd4ac771933 · outbound

This paper cites D., and Ryu, E.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently D., and Ryu, E

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.804362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation efd34516-c486-459f-aec5-ec2f26e5b657 · outbound

This paper cites Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.794463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 507b22de-18b1-41f6-95b7-cf0d0d60e9ef · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.784285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d979948f-07f8-44a3-aaa3-d167844b8f49 · outbound

This paper cites J., Blankevoort, T., and Asano, Y.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently J., Blankevoort, T., and Asano, Y

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.773945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81a27c7d-3539-498f-aa46-46ddf1a50af5 · outbound

This paper cites The mnist database of handwritten digits.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently The mnist database of handwritten digits

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:02.990024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431a81eb-4f7f-4acf-bf85-08e22846f3be · outbound

This paper cites D., Oko, K., Suzuki, T., and Wu, D.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently D., Oko, K., Suzuki, T., and Wu, D

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.758201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39584081-cdc2-4d49-ace5-10cda9aba82a · outbound

This paper cites On the Crucial Role of Initialization for Matrix Factorization.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently On the Crucial Role of Initialization for Matrix Factorization

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.748389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56ebdc6c-ead3-4e6d-a82a-f0a4cf4edfed · outbound

This paper cites Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.738387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8907fffc-5fe7-4ce4-b695-266863c44841 · outbound

This paper cites On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.728017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a02a1bd5-6bfe-41d8-91d0-007ca865b0b3 · outbound

This paper cites Decoupled Weight Decay Regularization.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Decoupled Weight Decay Regularization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.005405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8534b05-0c1c-41ae-9a79-02b67310ef2a · outbound

This paper cites Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.717706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7accefa-02ba-4a4b-ae4e-34a55b924577 · outbound

This paper cites A Kernel-Based View of Language Model Fine-Tuning.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Kernel-Based View of Language Model Fine-Tuning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.707829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d7d70b22-f8b1-43e8-ba2c-1dae1e596d28 · outbound

This paper cites PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.697700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d01205e5-5778-403a-ab06-1c4a8ffc92b0 · outbound

This paper cites A Riemannian geometry for low-rank matrix completion.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Riemannian geometry for low-rank matrix completion

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.018238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6e43e0-8d0b-4d36-9f01-88946a6ed686 · outbound

This paper cites A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.687093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 78bb1793-c050-4144-b60e-5d2916e1d605 · outbound

This paper cites A Simplified Neuron Model as a Principal Component Analyzer.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently A Simplified Neuron Model as a Principal Component Analyzer

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.676259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 134a84d8-2010-4563-b8e6-2f02bdc6fa85 · outbound

This paper cites Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.664861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 167604ef-acb0-461a-b34c-592b302f45bb · outbound

This paper cites Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.031517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc768797-f52e-4bce-8d14-c377b24005e1 · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.654583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c3141fd-cbbe-4660-a4b4-96e47c1c54be · outbound

This paper cites Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.645045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34fc5355-9046-40b2-a90d-db59b6197ba2 · outbound

This paper cites and Soltanolkotabi, M.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently and Soltanolkotabi, M

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.635190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f750e86f-5b98-49d8-beb4-12c6e515166e · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.625772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 010b8d47-0f95-446f-a306-a7f0c24637f2 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently LaMDA: Language Models for Dialog Applications

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.048322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18b1a333-15c3-4df6-8443-3912d4cb1bf4 · outbound

This paper cites Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.616071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e268e7c8-f651-4b0a-b807-bc01c9b88fc3 · outbound

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

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.054841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f9fd1ed-d886-4024-b520-385b263de2a1 · outbound

This paper cites Introduction to the non-asymptotic analysis of random matrices.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Introduction to the non-asymptotic analysis of random matrices

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-09T16:14:03.058338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c9f1f3-f119-4b9c-bc21-de003d2fa557 · outbound

This paper cites High-Dimensional Probability: An Introduction with Applications in Data Science , volume 47.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently High-Dimensional Probability: An Introduction with Applications in Data Science , volume 47

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.606503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1f35182-d39b-48fb-9393-962dfe66543e · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.596446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation efc7598d-937c-4a0c-a49d-5ffdd20b8165 · outbound

This paper cites LoRA-GA: Low-Rank Adaptation with Gradient Approximation.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently LoRA-GA: Low-Rank Adaptation with Gradient Approximation

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.586059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56fc75d1-1c56-4416-87cf-63106018aedd · outbound

This paper cites LoRA-Pro: Are Low-Rank Adapters Properly Optimized? In The Twelfth International Conference on Learning Representations, 2025.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently LoRA-Pro: Are Low-Rank Adapters Properly Optimized? In The Twelfth International Conference on Learning Representations, 2025

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.575882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1b47c16e-2246-4008-817b-e1b8c69bf693 · outbound

This paper cites Perturbation bounds in connection with singular value decomposition.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Perturbation bounds in connection with singular value decomposition

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.565991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de1421fa-a855-4c72-bb26-11ddf7b62211 · outbound

This paper cites V., Zhou, D., et al.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently V., Zhou, D., et al

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.555098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 42690d8a-29e6-46da-aaf3-796f06858e0b · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.544734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 58d9cd03-889e-4b3d-ad87-2e83f3840ab1 · outbound

This paper cites The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.535267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 47cf46d9-5a47-405a-b85e-9d6ead32a7cd · outbound

This paper cites E., Luo, J., Tarmoun, S., Mallada, E., and Vidal, R.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently E., Luo, J., Tarmoun, S., Mallada, E., and Vidal, R

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.525744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f556bbbb-d468-4029-97b9-acddbc9e9f4b · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.515757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9fd354b-8649-45f2-b69c-c6d8a678fa24 · outbound

This paper cites and Lee, K.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently and Lee, K

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.504847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 90295f17-eb6a-4516-8fba-f9427331ab91 · outbound

This paper cites and Pilanci, M.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently and Pilanci, M

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.494160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d25f34b1-4d2d-400c-a371-7a55549d135b · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.483887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d41c74c2-c68e-474e-afe1-32bab614e878 · outbound

This paper cites an unresolved cited work.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-09T16:14:03.473168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e5ca940e-b758-407c-a6bb-33188f247185 · outbound

This paper cites Y., Fu, J., Chen, W., and Yue, X.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Y., Fu, J., Chen, W., and Yue, X

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.462272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 09075420-d953-4799-b064-18baebc7f191 · outbound

This paper cites Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models.

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T16:14:03.451272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 40b1b03b-3966-4eb0-a99d-c160f9c3cbab · inbound

Decentralized Low-Rank Fine-Tuning of Large Language Models cites this paper.

Decentralized Low-Rank Fine-Tuning of Large Language Models LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:48.286017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697a3dbe-9bbf-4765-b1d1-41004303ff33 · inbound

LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail) cites this paper.

LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail) LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T21:56:28.103866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5746d7-93e9-4521-a468-ba60d607330b · inbound

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics cites this paper.

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:50.710627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c2d280-9bbc-41f0-88fb-86d9c5507173 · inbound

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model cites this paper.

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:16:57.382824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 28f8896a-54b2-4298-94b6-6a50faacb722 · inbound

The Hidden Power of Scaling Factor in LoRA Optimization cites this paper.

The Hidden Power of Scaling Factor in LoRA Optimization LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:08:21.934456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fff784f6-0818-4b94-9f82-4a35e93baf58 · inbound

Channel Location Constrains the Auditability of Subliminal Learning cites this paper.

Channel Location Constrains the Auditability of Subliminal Learning LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:44.420644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b72c719-4d81-4fd3-983f-4896b623a813 · inbound

Between Gradient and Natural Gradient: A Continuum of LoRA Initializations cites this paper.

Between Gradient and Natural Gradient: A Continuum of LoRA Initializations LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T00:26:41.122870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.