Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T23:22:20.741949Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2502.08905.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T23:22:20.741949Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
64 of 64 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 156914e9-0875-4a1f-b661-2b34e636fb97 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Dtllm-vlt: Diverse text generation for visual language tracking based on llm,
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 07b8d3a0-13f9-4825-9d30-fff4ee4bb992 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation,
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6b3fbfb2-c287-4b3a-8136-2091caab10b7 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Contrastive prefer- ence optimization: Pushing the boundaries of llm performance in machine translation,
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6c29e67a-01b0-49dd-baaf-a650e8db2e2d · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Designing heterogeneous llm agents for financial sentiment analysis,
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 345ba1ab-49d3-4239-96c6-724d1a968c86 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Toolqa: A dataset for llm question answering with external tools,
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 313bd9b9-3393-48a1-b5e6-11a84bc6bf22 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks,
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c093b9bd-c325-48b0-ae7a-760f2d94eee0 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection The power of scale for parameter-efficient prompt tuning,
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a90539e0-0cf1-42b3-87bb-aa4d33a18375 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Parameter-efficient transfer learning with diff pruning,
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1530f6a0-8edb-4a1f-823b-48e691a8d4e1 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection LoRA: Low-rank adaptation of large language models,
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d4ddf4e3-7d07-4b4a-80b8-9381cb9140aa · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Autolora: Automatically tuning matrix ranks in low-rank adaptation based on meta learning,
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 528359a7-f464-4943-8b99-d6f6ccd1e8fc · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Adaptive budget allocation for parameter-efficient fine-tuning,
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f60bc43d-b76c-44fa-915c-c46f230ce661 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Alora: Allocating low-rank adaptation for fine-tuning large language models,
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation cb97b640-3f7e-4d4e-8995-cf21e2fcac97 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e110f34-5562-4b07-bc7c-60e1f2167ae3 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cd543ea-000a-42f8-bde7-325810eacfea · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Unveiling lora intrinsic ranks via salience analysis,
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0dbb49a7-8355-4ff2-a2c4-1908b4a96ef7 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection GLUE: A multi-task benchmark and analysis platform for natural language understanding,
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation da6d89b5-cf11-4f39-b2eb-03c5215de3bd · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Efficient parametrization of multi-domain deep neural networks,
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 07c532fd-fae1-4a99-8134-3e8fc7341a66 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Velora: Memory efficient training using rank-1 sub-token projections,
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8e903b95-d8d8-4f35-8db7-45fc0cfa28d4 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Hifi: High-information attention heads hold for parameter-efficient model adaptation,
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation fd2120ea-e1b8-4715-9a11-f4447c58949e · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Bitfit: Simple parameter-efficient fine-tuning for transformer- based masked language-models,
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4e5bda04-9ed4-4bdb-a057-09ae1b3682f0 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac3e3331-17ec-4e35-94c5-52199248e275 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection VeRA: Vector-based random matrix adaptation,
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9237c61f-3f78-46e5-9ffa-612e79581e0e · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection LoRA+: Efficient low rank adaptation of large models,
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4a76f080-a544-4e7b-82ae-3c25df6ed50f · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection DoRA: Weight-decomposed low-rank adaptation,
Reference 24
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation cec22598-bb7b-4f5b-9ed1-d482b5c15c0b · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Qlora: Efficient finetuning of quantized llms,
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 577d88d8-f4c6-46c6-b4ab-ec6f386af1b0 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Tied-lora: Enhancing parameter efficiency of lora with weight tying,
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 254ac9b7-a447-4767-b19a-70158068e712 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Lora+: Efficient low rank adaptation of large models,
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 114a2b6c-2305-4ba0-a18f-be93885a6f2b · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection LoRA-pro: Are low-rank adapters properly optimized?
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f1f867d2-76bd-4a84-993e-6bb42b449032 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Hydralora: An asymmetric lora architecture for efficient fine-tuning,
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f0fca4b5-255a-44eb-b3ab-d917ae877c9a · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Sparse low-rank adaptation of pre-trained language models,
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 053e2748-19e1-4562-98af-8d689db1f614 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Gradient descent provably optimizes over-parameterized neural networks,
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4bb6158b-e3eb-4dc6-9836-c29a00652103 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Visualizing the loss landscape of neural nets,
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 10fb0e32-78d2-467f-965a-f3749589e2e6 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Meco: zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation,
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9181c037-48c7-4bee-9a86-649d6d2d6509 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Unresolved cited work
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 520853a7-e6e5-4b15-82a9-41ec1dfbc421 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Generalization bounds of stochastic gradient descent for wide and deep neural networks,
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6f40befa-3e4a-44e0-af8c-68f17b509cf4 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Generalization properties of nas under activation and skip connection search,
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 080bc6aa-f9b6-4507-8730-2f1a03d25a76 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing,
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6bd1a59f-f17c-4269-b1a0-6db4cdae15f6 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection GLUE: A multi-task benchmark and analysis platform for natural language understanding,
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1647e718-579b-44f4-a6ad-6db063ead0c6 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection SQuAD: 100,000+ questions for machine comprehension of text,
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0b63be53-6c84-4277-b5e4-641fc40efaa7 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Know what you don’t know: Unanswerable questions for SQuAD,
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 979ad495-1e65-4ea5-be0b-6a0304004ae4 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection The Llama 3 Herd of Models
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8aa3c1db-8218-4bb4-9d66-18c33b7cf9d2 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e46c3201-d875-472c-b862-927997b779d5 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection RoBERTa: A Robustly Optimized BERT Pretraining Approach
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6f5cf2e-fb0a-40ac-a31b-03946e616a48 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Magnus and H
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a087289f-35a4-4850-8180-8758eda8cab7 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Unresolved cited work
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6016e1fe-1ddb-426c-bf66-3a628c417a7b · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Parameter-efficient transfer learning for nlp,
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ced63b0d-d566-4804-8710-5eef14af44bb · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Adapterfusion: Non-destructive task composition for transfer learning,
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 330972af-c10f-428f-8ba0-43810babcf15 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection (vii) LoRA+ [27] employs different learning rates to update the low-rank matrices
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 317b0b82-7ff3-407c-b8a8-eaa542980a97 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper
Reference 49
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 63ff2f14-3d0d-4045-a338-f0caa06613bb · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Limitations
Reference 50
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7e7417d2-a811-4b0e-8e78-4af49850f0e3 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not include theoretical results
Reference 51
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5e53a778-8094-4001-9c94-30bbde956e13 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not include experiments
Reference 52
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e465f94a-3f96-46e0-8801-e1524d9b9f25 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection All the datasets we used are public
Reference 53
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 795902c1-0969-48fb-9718-27833f040db0 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection For additional experimental settings on various benchmarks, we provided the details in Appendix D
Reference 54
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4130467a-18b2-4dd4-b945-f879bdd14d96 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection We have run our experiments multiple times with different seeds and provided the mean and standard deviation values in Section 5
Reference 55
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 62148de5-31bd-4745-8cee-528b8d32e83a · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not include experiments
Reference 56
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 486e6e0b-819d-4484-9e05-c2da5beee003 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ec0e2f8d-c2ad-4590-89cf-271b04a3a04c · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that there is no societal impact of the work performed
Reference 58
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6e885e51-4b6d-4fdb-ab4a-db9212839b9e · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper poses no such risks
Reference 59
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f48657ea-6c94-4feb-8943-0b2275d8a2df · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection We have properly cited these resources in our paper
Reference 60
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7ebbf6da-f897-4ccc-93e8-522af3ade967 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not release new assets
Reference 61
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 22c03add-6f7f-4cc3-8f90-2d1945eb44b3 · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects
Reference 62
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f95ab010-44fc-4c54-a638-f564dfdfc86a · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects
Reference 63
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d1f7ad08-7e5a-4870-8964-f4cbdd9dfc4f · outbound
DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection Answer: [NA] Justification: We utilize LLM only for grammar and formatting purposes
Reference 64
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
No inbound Pith citation observations are available.