Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning | Paper Citation Record

Observation 7fa26ea9-22d6-410b-9502-ee123d636ba5 · outbound

This paper cites Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.917747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26b7a2cf-c658-48c5-a3e3-b6130722bcb6 · outbound

This paper cites Classification Problem Solving.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Classification Problem Solving

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.924506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65bbd1af-60db-42b6-9d27-cc161d761027 · outbound

This paper cites , title =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning , title =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.928468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66dc00e3-3dd3-4967-a658-ccefad01e13b · outbound

This paper cites New Ways to Make Microcircuits Smaller---Duplicate Entry.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning New Ways to Make Microcircuits Smaller---Duplicate Entry

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.932393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7a9da4-fb10-4d20-9f15-31774e18542f · outbound

This paper cites Clancey and Glenn Rennels , abstract =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Clancey and Glenn Rennels , abstract =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.936335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80393bd7-7560-4cd6-8120-c8e328eebb5e · outbound

This paper cites and Rennels, Glenn R.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning and Rennels, Glenn R

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.940398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ab3240-9004-4a7d-9180-1f601e3e5dee · outbound

This paper cites Poligon: A System for Parallel Problem Solving.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Poligon: A System for Parallel Problem Solving

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.944452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b20c1548-50fe-4842-addb-481953e7b243 · outbound

This paper cites Transfer of Rule-Based Expertise through a Tutorial Dialogue.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Transfer of Rule-Based Expertise through a Tutorial Dialogue

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.948295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73235bfc-83af-487e-ab9b-5b7a3c431339 · outbound

This paper cites The Engineering of Qualitative Models.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning The Engineering of Qualitative Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.952718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02cbb07-5581-4f4f-9ab1-d3ce589d5f58 · outbound

This paper cites 2023 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2023 , eprint=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.956350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a97d2755-0259-48a5-9c36-fea325e50c59 · outbound

This paper cites Pluto: The 'Other' Red Planet.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Pluto: The 'Other' Red Planet

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.960384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 612f8ce0-c1b9-47d7-9ff1-4054a0f224e9 · outbound

This paper cites Attention is All you Need , url =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Attention is All you Need , url =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.964264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db56a1f1-39fb-43f8-8ba4-a38fd9416905 · outbound

This paper cites 2020 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2020 , eprint=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.967985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3f2728d-3bae-47cf-b602-d14e3e122139 · outbound

This paper cites arXiv preprint arXiv:2504.07139 , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning arXiv preprint arXiv:2504.07139 , year=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.971761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a918ba-39a8-4fb5-85d2-72fffde59e0d · outbound

This paper cites Nemotron-4 340B Technical Report.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Nemotron-4 340B Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.975473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c3b695-b9e4-4f82-8139-f22506109253 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Qwen2.5-Coder Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.980152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa580fa-f4cc-4517-8dbc-f6a5b98b976c · outbound

This paper cites The Llama 3 Herd of Models.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.984366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe18244-8f27-40ad-805f-9879e8c9226f · outbound

This paper cites arXiv preprint arXiv:2512.13607 , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning arXiv preprint arXiv:2512.13607 , year=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.988073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d201ae-1133-4d3c-a8f8-7791e2b0faa2 · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning , year=

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.086310Z

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 63f9a6ff-2722-4a98-bdb1-3722d656b668 · outbound

This paper cites Magistral.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Magistral

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.995426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f317759-341d-4707-b2e2-42c57b7a81f2 · outbound

This paper cites OLM o: Accelerating the Science of Language Models.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning OLM o: Accelerating the Science of Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:01.999388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a67b40-b7cc-410c-8037-0784854f92ff · outbound

This paper cites Smith and Hannaneh Hajishirzi , booktitle=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Smith and Hannaneh Hajishirzi , booktitle=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.003544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61a751c-399a-4277-8c2f-bbc7ddefb95a · outbound

This paper cites Olmo 3.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Olmo 3

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.007167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15f43113-0a55-4b26-98f9-083d31e4a338 · outbound

This paper cites DeepSeek-V3 Technical Report.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning DeepSeek-V3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.011121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d58dd51-2d8a-4357-874d-23b8d0dad506 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.015146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2464088d-5454-427f-9193-3e1483b0c35a · outbound

This paper cites 2025 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2025 , eprint=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.019052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ec2a1a8-c8c9-4d27-afe9-3f40f7de60cb · outbound

This paper cites DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T17:11:02.669339Z

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 273aad41-1666-4d91-9c19-9c8f799432fe · outbound

This paper cites 2024 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2024 , eprint=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.053512Z

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 6ed44052-af84-4559-99af-d3aa00f0ec60 · outbound

This paper cites , booktitle =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning , booktitle =

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.042096Z

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 9583d764-883e-4022-aa68-937a08b70579 · outbound

This paper cites Journal of Machine Learning Research , year =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Journal of Machine Learning Research , year =

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.031093Z

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 6591fbcc-deeb-4f5b-b4d0-fec4f9aa51f2 · outbound

This paper cites Automatic early stopping using cross validation: quantifying the criteria , journal =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Automatic early stopping using cross validation: quantifying the criteria , journal =

Reference 31

Resolution: verified exact; doi, observed 2026-08-08T17:11:02.301427Z

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 c180e444-a76f-4c92-8cc2-b401525f67da · outbound

This paper cites Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.044038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 176b6445-575f-4342-b517-b591c940cc8c · outbound

This paper cites 2025 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2025 , eprint=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.019032Z

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 1744dbbf-a95a-4f2e-a47a-22f6bb99c0af · outbound

This paper cites 2026 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2026 , eprint=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:03.006807Z

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 095f0c91-3102-4b46-ae10-1bed3c8f5705 · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning The Thirteenth International Conference on Learning Representations , year=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.055894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0baa6942-2abd-45e9-abbe-e09149c70d4e · outbound

This paper cites Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

Reference 36

Resolution: verified exact; doi, observed 2026-08-08T17:11:02.282262Z

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 66a37c46-daed-4216-b382-17d2c676a840 · outbound

This paper cites How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.064468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff985bd7-3d3b-418c-a9fe-d879a1191172 · outbound

This paper cites 2025 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2025 , eprint=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.989256Z

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 0abe4e0d-af11-4f41-a531-3eac5ba860a0 · outbound

This paper cites 2026 , url=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2026 , url=

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.976157Z

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 cb812d02-a546-4f08-bfbe-d200173fc496 · outbound

This paper cites From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.075922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d7be7d2-82ff-4b47-86af-e1e6c83404cc · outbound

This paper cites Advances in Neural Information Processing Systems , editor =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Advances in Neural Information Processing Systems , editor =

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.965105Z

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 ef436195-50ef-43d6-a346-46c4aa52fbb9 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.953961Z

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 97dd98aa-8cf1-4c5c-ba55-d683f409f3a5 · outbound

This paper cites C ommonsense QA : A Question Answering Challenge Targeting Commonsense Knowledge.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning C ommonsense QA : A Question Answering Challenge Targeting Commonsense Knowledge

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.088698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b246ed59-5f14-4d4b-884b-1fe8fce69efc · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.092641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe7e759-940c-4be9-b117-2d9680453395 · outbound

This paper cites Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.096257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 851b3790-a830-4098-9d6d-95fa5f633b1e · outbound

This paper cites 2021 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2021 , eprint=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.099872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a2511f-8222-45b0-812f-6ca696536dfe · outbound

This paper cites and Gardner, Matt.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning and Gardner, Matt

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.103333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 902d7c09-649c-490a-ab60-b44648bc0619 · outbound

This paper cites 2018 , eprint=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning 2018 , eprint=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.107030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575b65b2-470e-4897-9452-0aa3da73b693 · outbound

This paper cites H ella S wag: Can a Machine Really Finish Your Sentence?.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning H ella S wag: Can a Machine Really Finish Your Sentence?

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.110927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34cba346-132b-4cc2-beb4-eaec0fec7fdc · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.114583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a610b19-f81d-477c-b00a-57241a0a8892 · outbound

This paper cites B ool Q : Exploring the Surprising Difficulty of Natural Yes/No Questions.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning B ool Q : Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.117975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9440e8ea-68af-44d3-83ef-5587541a58bc · outbound

This paper cites Proceedings of the Conference on Health, Inference, and Learning , pages =.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the Conference on Health, Inference, and Learning , pages =

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.121362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf6e7922-31ca-4789-8784-ade051d97fbd · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.125832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b0beaef-6838-46d2-8f2b-831ca045f6ac · outbound

This paper cites Proceedings of the 2022 conference on empirical methods in natural language processing , pages=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the 2022 conference on empirical methods in natural language processing , pages=

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.917434Z

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 222a1d89-64c8-40b8-97dc-ec19b59e88fe · outbound

This paper cites Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.133177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed7522e3-e34d-4adf-b026-b1d0bff25497 · outbound

This paper cites International conference on machine learning , pages=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning International conference on machine learning , pages=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.136783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff6d394a-78c2-4a3f-83aa-5e5d3916c931 · outbound

This paper cites Advances in neural information processing systems , volume=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Advances in neural information processing systems , volume=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.140289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a82404f-7951-4552-85b8-971ab7801c3e · outbound

This paper cites Advances in neural information processing systems , volume=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Advances in neural information processing systems , volume=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.893010Z

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 829e4c4a-7b91-425d-ab22-aaf48cd68d26 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Advances in Neural Information Processing Systems , volume=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.147245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebbc110b-d718-43fd-9b49-163849057606 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.874722Z

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 cbc188b6-4755-47e8-8a31-01a7ef8f67ec · outbound

This paper cites SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.153955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3142d9-9c37-4bad-b1a6-fea1d8088ebc · outbound

This paper cites arXiv preprint arXiv:2603.21606 , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning arXiv preprint arXiv:2603.21606 , year=

Reference 62

Resolution: verified exact; raw_fallback, observed 2026-08-08T17:11:02.623407Z

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 3e21ff3b-aaee-48db-b830-59de57f52ae3 · outbound

This paper cites arXiv preprint arXiv:2505.18738 , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning arXiv preprint arXiv:2505.18738 , year=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.161150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a8c7e3-a17d-40f7-b4ae-336e2dcde4b2 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning LoRA: Low-Rank Adaptation of Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.164466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0628d89-d5e9-4bdf-846c-3e47b31f96a0 · outbound

This paper cites Proceedings of the 36th International Conference on Machine Learning , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the 36th International Conference on Machine Learning , year=

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:11:02.861214Z

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 a34dbec1-d63d-4b7c-a627-7db9e58f1e33 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.172024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9929ffa-4503-4b52-8aa6-f7e6a9ef0135 · outbound

This paper cites Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , year=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.176825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 801ec374-b896-46de-9b5f-e2fbe2c4e803 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning QLoRA: Efficient Finetuning of Quantized LLMs

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.181412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba074b6f-cdc0-4e93-bc70-8f533cff1713 · outbound

This paper cites AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.185238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd21da5b-ecb2-4f2f-a5a7-220bb84837e4 · outbound

This paper cites arXiv preprint arXiv:2308.10792 , year=.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning arXiv preprint arXiv:2308.10792 , year=

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.188994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd40e0c-24eb-451e-9d74-b021d0a861be · outbound

This paper cites DoRA: Weight-Decomposed Low-Rank Adaptation.

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning DoRA: Weight-Decomposed Low-Rank Adaptation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.192352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 613486fe-4142-4316-9292-2f82f01213ad · outbound

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

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning LoRA-GA: Low-Rank Adaptation with Gradient Approximation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T17:11:02.195801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers