Pith. sign in

Paper Citation Record · LEDGER

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

As of 11 August 2026, this Paper Citation Record lists 100 of 101 outbound references and 4 inbound Pith citation observations for arXiv:2502.00264.

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

pith.paper-citation-record.v1
2502.00264 v2

Coverage vector

measured 100 of 101 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T19:44:21.097412Z

measured 104 of 104 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T12:34:51.331297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T10:39:45.071517Z

Reference resolution

100 of 101 outbound references displayed

  • verified exact2
  • verified fuzzy41
  • unresolved57
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ecfa3128-87f4-474c-b522-0da9ec074888 · outbound

This paper cites Git re-basin: Merging models modulo permutation symmetries.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Git re-basin: Merging models modulo permutation symmetries

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.564384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.564384Z digest=sha256:e9dbd31131300a08846c4bf23b3b972c397be5153066dd8ad00c07bef6e95750

Observation 3b0e67e0-61d5-49ce-aff7-1cf04660f678 · outbound

This paper cites and Jodoin, P.-M.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Jodoin, P.-M

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.569562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.569562Z digest=sha256:301d1243b4ecb82f9cc9a79113b4cfa5b5f1dd06bf706956fe2af900e77a8da7

Observation cd7a5b1d-3355-41a5-b063-ce45dd141fed · outbound

This paper cites Ensemble of averages: Improving model selection and boosting performance in domain generalization.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Ensemble of averages: Improving model selection and boosting performance in domain generalization

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.575225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.575225Z digest=sha256:daf1e95593feb32fb295d9945ff26c439e8bde9697d1f3e930a0ede2a5403e8d

Observation e27fa703-33d8-4ce7-8913-5806fb98916b · outbound

This paper cites Layer Normalization.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Layer Normalization

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.580106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.580106Z digest=sha256:7810f18d4ef5146ed83de60b7b011e73a2ce61aeb28dedfc6d83be9a062736a4

Observation 7331a746-94f5-48f0-b9f4-01a8e2d9d90b · outbound

This paper cites Symmetry-invariant optimization in deep networks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Symmetry-invariant optimization in deep networks

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-08-09T19:44:21.421754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.585826Z digest=sha256:0ff80edf0d9257d904c16c7d684260ad7939e423c9451780ef3cf34200a1bafb

Observation bad5ec29-e458-4316-9fde-286b2f8efe07 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.592107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.592107Z digest=sha256:435bcfd05ebb14d960a420cf1f04a94807322a714227e7b828a162503662ed9d

Observation 561633e0-644c-494c-95ab-4d0a19569666 · outbound

This paper cites and Klinger, R.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Klinger, R

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.598186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.598186Z digest=sha256:2c2d0358d0d03563fdbc1598f273349fe591c2bad6bfcb131c76d8f2567b673f

Observation c81f3d45-98b9-4b92-b846-a09c76a88315 · outbound

This paper cites Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.603005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.603005Z digest=sha256:b7b7f62bcc2439c9fa6b38a489a2af381556e2d5c53a6295e6a2336a8bc100d8

Observation f6604e74-1511-4393-aad4-7a46b40889db · outbound

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

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.609457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.609457Z digest=sha256:be8b32144c298f31e13341709505a218640dd897f200137d26fc6dc31462eac7

Observation 76a104ee-c481-4e5d-97d4-3aeca706bc4d · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.614564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.614564Z digest=sha256:df468e35eaceef045e56bb2b0bcd2eb62e8a3555b7fc05462397ba3b473763e6

Observation 50c2b045-cab7-46d6-b0a8-bb09fe4643ea · outbound

This paper cites Swad: Domain generalization by seeking flat minima.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Swad: Domain generalization by seeking flat minima

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.618979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.618979Z digest=sha256:abd4c1ee0f9247542f1789c1b3d120f65bce9654d9f895d1abebc3c2eed3d9f5

Observation 865c329d-5439-4f9e-a640-63e5e7e8f7b1 · outbound

This paper cites Fusing finetuned models for better pretraining.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Fusing finetuned models for better pretraining

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.624731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.624731Z digest=sha256:8ed955aadee7037f6a35cd7d6651e8ac6b3a04c1a093a305ba2d587766fcb2a4

Observation ea87dcfa-bd53-4f38-a11b-54412b942bb2 · outbound

This paper cites V., and Manning, C.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion V., and Manning, C

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.629756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.629756Z digest=sha256:9a74a0563cca009e02233c832358bca05c4a8d50defbc42c25b14a7f6d088443

Observation 35c3441f-dc36-46bc-b424-d8514ca8020a · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.634237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.634237Z digest=sha256:69dd574f9be1fd8803b4a3ceb6021b1fda829a0bf982eeb45845c0f48ffc3f81

Observation 8cf6c8da-b1e3-40e2-90b6-745a7e538d94 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.638635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.638635Z digest=sha256:5025ce6c756fcac2bc1b6249a744a37227ec5f405d690b6df308f21be52a44d8

Observation 7e9fec02-e709-4acf-bb95-d1d3ee4b3005 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.642848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.642848Z digest=sha256:b1ed4e0bf39d75b75f78b2624be73d0505570ed5998a0859a7deeb892e57bfb4

Observation 357afd93-62e3-488d-82a0-8a1bdee5ac17 · outbound

This paper cites A survey on ensemble learning.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion A survey on ensemble learning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.646846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.646846Z digest=sha256:efa5ce86c8e0cf7c2b92d5a9b55d686ef9847476f0c70c1013ea58b38518f6d0

Observation 803eb7dd-fd0d-4719-9b12-00cb648cdd76 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.651126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.651126Z digest=sha256:b0913aca72f36f5d6220ab51efa59d98a144c921fbe77fbbdc359239143a52b3

Observation c248e0ac-9417-4d39-9487-15b899ec07ce · outbound

This paper cites S., Hu, W., and Lee, J.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion S., Hu, W., and Lee, J

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.656356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.656356Z digest=sha256:2d42351b3249ed2d043b1e42847aeb3ec8996c7eb732d01b5691c3adf0deab14

Observation eca5c0eb-8d8e-4bb6-a065-37b3437611f1 · outbound

This paper cites The role of permutation invariance in linear mode connectivity of neural networks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion The role of permutation invariance in linear mode connectivity of neural networks

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.660861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.660861Z digest=sha256:14593ed33d1cb930754b20c520b9adc935f2b37a1d4b42aab09eb598e744ec3c

Observation a3192bc5-47c0-472a-89b0-81c3acda4270 · outbound

This paper cites Proving linear mode connectivity of neural networks via optimal transport.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Proving linear mode connectivity of neural networks via optimal transport

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.665316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.665316Z digest=sha256:ebecb057a509d39bfe2b7730e752439c523c6d6cecf431f5a518fa6656859333

Observation 36f5355c-23ae-4563-b756-2712eb3a6353 · outbound

This paper cites and Amari, S.-i.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Amari, S.-i

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.669604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.669604Z digest=sha256:2e5c8ea83262a3780ec670faa0f6745ef158ebaa6dd87d2b99639c7cfd91069b

Observation e762f9b6-44d8-4d0b-bfa2-b8ea75649f0c · outbound

This paper cites Deep sparse rectifier neural networks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Deep sparse rectifier neural networks

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.673929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.673929Z digest=sha256:b45240953da2ad8cc4bdca5dd33ba47fe65a6f638d72adc510f7a391275865eb

Observation a2fcf8c6-d167-4fac-b8ac-4f592eefcf54 · outbound

This paper cites On the symmetries of deep learning models and their internal representations.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion On the symmetries of deep learning models and their internal representations

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.678361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.678361Z digest=sha256:2460fae135b94ee0a785adea8333e292b8193b885abb61bb26be03d99903cf93

Observation 0d2048ed-740f-419e-a61b-87c105d22854 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.682652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.682652Z digest=sha256:3f7c289c46b8ce32dbe91d9359229f0f8556e0f3ff187a77f06d5529253ac379

Observation c6893be8-47b3-48a8-a107-86869f133300 · outbound

This paper cites Hidden symmetries of relu networks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Hidden symmetries of relu networks

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.686749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.686749Z digest=sha256:ef5cd3977cd0437b6db00dbc1c8aaf0eb983699400188df991cc2bf11c730eaa

Observation aef45f0c-ac87-47e1-8413-5994e00c8053 · outbound

This paper cites A., and DeCoste, D.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion A., and DeCoste, D

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.479580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.691402Z digest=sha256:5a7c4d99c90a9961d4c354ad8d1d1b0f7966162ea6c242da5895eed3e1efd668

Observation 83528031-835f-4852-8f7b-96df32de7d7d · outbound

This paper cites Model merging and safety alignment: One bad model spoils the bunch.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Model merging and safety alignment: One bad model spoils the bunch

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.463257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.695941Z digest=sha256:7dce112b1b9e4d5aecfb0ad61dac5380ae019f627080f5e58add91dbdc1561b3

Observation c74957ab-fc47-48e3-8d6a-1542ab203651 · outbound

This paper cites Deep residual learning for image recognition.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Deep residual learning for image recognition

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.700299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.700299Z digest=sha256:c0045e719deaf031d986b89fb128198ba6d1ad7288f3d81dbc738b83dabd925d

Observation 51106918-7806-4bff-8aa4-c02c09f84b82 · outbound

This paper cites Deberta: Decoding-enhanced bert with disentangled attention, 2021.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Deberta: Decoding-enhanced bert with disentangled attention, 2021

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.435906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.705479Z digest=sha256:3292e279cfa140c07f14250797f478118ed3e38352980d5f31c5e73bbd5798d6

Observation cb74234e-05cd-4457-b399-05ddec109855 · outbound

This paper cites Explaining graph neural networks with large language models: A counterfactual perspective on molecule graphs.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Explaining graph neural networks with large language models: A counterfactual perspective on molecule graphs

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.417683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.710368Z digest=sha256:bec89062d5dc3143242ea2edd722e2222ea30646ba9ceac98bc676af03b05c44

Observation 4980425f-d01c-4ea4-945f-87ca22626206 · outbound

This paper cites On the algebraic structure of feedforward network weight spaces.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion On the algebraic structure of feedforward network weight spaces

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.399998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.715478Z digest=sha256:3c1945d9b0620312acc7565864c2d9b7e32d90bea4348e6ce5de1d8cfd87f95d

Observation 25aeea0b-cb9e-4a4a-b71e-5b80a90b6634 · outbound

This paper cites O nto N otes: The 90 \ In Moore, R.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion O nto N otes: The 90 \ In Moore, R

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.382351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.721815Z digest=sha256:507be15bb9904e3298165429849bba6a565a8e108ca86f7df8e0c68ee4d04684

Observation b58e1aae-219d-45da-bb54-99399d9adc48 · outbound

This paper cites Emr-merging: Tuning-free high-performance model merging.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Emr-merging: Tuning-free high-performance model merging

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.365387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.727392Z digest=sha256:8c09a40cdeb24400e7dc1215909b175c774a622fff454fc59d4be95300f0a2aa

Observation 1df5214a-177b-492d-84e0-a5dde93e8526 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:22.349268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.733585Z digest=sha256:ed2c772d9e621c56946ea855922cf39f259d4c6f779cc41c33c1cf00e0d79450

Observation 54ada3e8-aad8-4304-8268-fe673808f3bb · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:22.332190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.740760Z digest=sha256:311ffcddad0cfedfc586438e513863ccf933ea6759042402ff5f510014eb3437

Observation ba09ea98-c418-49ea-8286-6fdfd3becde1 · outbound

This paper cites Dataless knowledge fusion by merging weights of language models.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Dataless knowledge fusion by merging weights of language models

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.314485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.747572Z digest=sha256:1c63d2d0d2231ae39915cb1aeacebe64e002a24e36200d60522ccef736458703

Observation ec03ee57-5a99-4b43-8329-3079635ae878 · outbound

This paper cites A solution for the best rotation to relate two sets of vectors.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion A solution for the best rotation to relate two sets of vectors

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.752868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.752868Z digest=sha256:fc266c1840a246ea8624620c976296760e2cddbdab5ff205dbcf32070cd1b678

Observation 73e8eb8b-9500-4390-8348-d11db648a2e1 · outbound

This paper cites Scale equivariant graph metanetworks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Scale equivariant graph metanetworks

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.287067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.757780Z digest=sha256:2009fdfa87f414e87bdb55fe5f5f22bbb312328d1c8cc43167e439f82056774d

Observation ea272075-6123-4ecb-a3fe-f0845d198249 · outbound

This paper cites Federated Learning: Strategies for Improving Communication Efficiency.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Federated Learning: Strategies for Improving Communication Efficiency

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.762049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.762049Z digest=sha256:417e93d7ab72c67791087dadd6ba2a203236aef0ebbb25f3e116f36cf86253ed

Observation 900dbb94-406e-4e82-b9fb-35efafb27a7f · outbound

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

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Learning multiple layers of features from tiny images

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.766797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.766797Z digest=sha256:cf1c1083513c8052a44390cbd8822a8ec8caef6c16246fceaaf08efae3176c22

Observation aeefff41-056f-4cdd-95d1-56c318eefe3c · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.771867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.771867Z digest=sha256:4344337035aeee9862b099f6933416b7c5b107ffa030b2fafb90ab1069cf9f09

Observation 969ef17a-e726-4461-9913-d0a901e9b91a · outbound

This paper cites L., and Tanaka, H.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion L., and Tanaka, H

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.248783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.777296Z digest=sha256:d2914830822683d145b2987708eab17dc0f8aac6dc66394de73368a044ff38d2

Observation 371c50b8-749d-46a8-b485-6107c5470f10 · outbound

This paper cites Simple and scalable predictive uncertainty estimation using deep ensembles.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Simple and scalable predictive uncertainty estimation using deep ensembles

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.782022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.782022Z digest=sha256:67e48c54b98816ef6707fb5c08e8099e87f19548700e23b41e582b55be46a2a4

Observation 2846637c-4ac9-4992-8512-0f5e3ec07bae · outbound

This paper cites Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.221557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.787046Z digest=sha256:197f1a2195246de77eef5144cda3b89a2ca253376bad112a2005d756e73cfb4b

Observation 62d684f1-e374-4a5c-bdbb-9920f3fc0207 · outbound

This paper cites A., and Zettlemoyer, L.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion A., and Zettlemoyer, L

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.205636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.792013Z digest=sha256:e3de5f27cc091ce0476cb249153d71eccfbf3410c48ce3e28a6b69e4c5dc8928

Observation db70bbcc-cf4a-42a1-87dc-c12f63fd3890 · outbound

This paper cites Deep Model Fusion: A Survey.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Deep Model Fusion: A Survey

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.797091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.797091Z digest=sha256:022e5c15d676cf78e6f2776f90a40b1c3f181791616cfb4e55dd4d2ab07432e3

Observation 4803c2e0-9745-44d8-bb24-5c793cd6d7c7 · outbound

This paper cites T., Lorraine, J., and Lucas, J.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion T., Lorraine, J., and Lucas, J

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.190758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.801856Z digest=sha256:362d2f95f18530d47f9bf5b78f9ddcd4f8308fe54f22bcacbfc1a809011e6307

Observation 51be4c48-c9c6-4241-b788-cebd1eb03709 · outbound

This paper cites The empirical impact of neural parameter symmetries, or lack thereof.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion The empirical impact of neural parameter symmetries, or lack thereof

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.174166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.806843Z digest=sha256:6dc9eb3d30e4849a99e3e7164436590bf06f8b20303c5f47eda9a0c21815db6b

Observation f6070c8e-d5ab-4b3b-b190-ee528fd3c1db · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.813200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.813200Z digest=sha256:bac4581207d1011a8cdda934952bbc74a459d89572045bb4587070749385dcb6

Observation 1ddfe28a-b692-47e2-adbf-ba74835d8cc8 · outbound

This paper cites Symmetry induces structure and constraint of learning.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Symmetry induces structure and constraint of learning

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.156242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.821597Z digest=sha256:f648a00b8f0ee45473304ea17125a0201e25f03265a9f653c5ada969c8c7e3ed

Observation 191b8c92-b467-4cc3-b0eb-6a053bcef2b7 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Swin transformer: Hierarchical vision transformer using shifted windows

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.828517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.828517Z digest=sha256:1c70677785143340ebd8d752f89f43473d0bd1ffbf23b743bdd19a87afaa035e

Observation 607ef03e-134f-49fa-8cbc-6a924ca5f869 · outbound

This paper cites S., Bigelow, E.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion S., Bigelow, E

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.127133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.833619Z digest=sha256:16b72f6a900a64a6aba081bf3033cba40f63f707422a7a8851e963291d0fbb86

Observation 78a583c7-4eec-4fbb-aa9a-73a5e863c71b · outbound

This paper cites and Toth, P.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Toth, P

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.108256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.840570Z digest=sha256:0cdc11810e9f955294078c9da72a6edd4358582b265af2e0f6236813acb4a42e

Observation 2d236c43-0356-4414-9db1-d9fc58cd009f · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 55

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:22.090713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.846069Z digest=sha256:87180024ff78d52cb243763ac2539ee45c3de993f1b0f841d5ea80fb4be464cf

Observation b0e08ec4-7a04-4667-aaa0-6f7f152fdcc1 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 56

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:22.073467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.851698Z digest=sha256:f71ebb68210431fc798a906d97d0c4d753c1899ad986f4f22b5d0630ccecf1ca

Observation 65d7c754-24f2-4d1e-bb15-ea86cfe2fbf4 · outbound

This paper cites G-sgd: Optimizing relu neural networks in its positively scale-invariant space.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion G-sgd: Optimizing relu neural networks in its positively scale-invariant space

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.055585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.857720Z digest=sha256:7cce845ec7c4e978c70ffb2128e6aefc612a3f1135f9c6da8602b8d444e86def

Observation 74eb8375-a3c9-440e-9cd8-72ce113b6747 · outbound

This paper cites and Hinton, G.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Hinton, G

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.036300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.863437Z digest=sha256:ee88f4998dd9422a4e2dfe43dd38959a53504fdfaeab9348dd40402d78af7318

Observation 8ea15f1c-14c2-4c77-85b1-135485a789ea · outbound

This paper cites Equivariant architectures for learning in deep weight spaces.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Equivariant architectures for learning in deep weight spaces

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.019241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.869098Z digest=sha256:9e37819e10a6b8aba48bafa0d3aa380436ab9148a9554d1a4563ef9b99473366

Observation d5db7c16-b255-4417-8a21-d7b33c55bcac · outbound

This paper cites Equivariant deep weight space alignment.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Equivariant deep weight space alignment

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:22.002014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.878227Z digest=sha256:c51716a9c32878489201751a87280330e532a76bad0a0a6f05bdac15bfb5a788

Observation 34a13bb0-23bc-49e4-9e3e-36a7c90ed930 · outbound

This paper cites R., and Srebro, N.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion R., and Srebro, N

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.984608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.883949Z digest=sha256:63096e23ac6933cff27e2bdcf3c1a0f7176500b7507d44ce32f0ff20599fe400

Observation 5aa6e507-018f-42ba-b478-ca5a1f3a2ebd · outbound

This paper cites How Do Vision Transformers Work?.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion How Do Vision Transformers Work?

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.891764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.891764Z digest=sha256:34fb561c4aa45c6b1a9fcad6be2e64919b0ab58f4a9ad3f34e41029de55250f8

Observation 2f001cf5-ba51-45d2-82e1-dc3e4283306e · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 63

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:21.970138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.896797Z digest=sha256:b83cd0b3bbaffebb8fe5418748e0d0f1e3930c7207291413801a151c523dd925

Observation 1a354603-3f7b-42c4-9b2d-bf2518d058e4 · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.901687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.901687Z digest=sha256:6dd11b2925105e1e3c8dc1d5c82274a290ac00fc52a2fd0802497d398450f3a2

Observation fb8628fc-cc8b-48d7-99c3-c048c83f93d1 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.908057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.908057Z digest=sha256:88aa0123f82a0a0088d7241a9525eb732f89008cb9942b405dab73f011605754

Observation ed9d6df6-2d37-45d8-98ef-5654a5200f08 · outbound

This paper cites Diverse weight averaging for out-of-distribution generalization.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Diverse weight averaging for out-of-distribution generalization

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.913377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.913377Z digest=sha256:8192d68873744f1f7e387beb7a8ce81b4fde6ab4af94195faa0034058ea6419a

Observation ed3eb8e6-0856-4baa-ab41-22b2f6bdb778 · outbound

This paper cites On permutation symmetries in bayesian neural network posteriors: a variational perspective.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion On permutation symmetries in bayesian neural network posteriors: a variational perspective

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.919579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.919073Z digest=sha256:19c5345d91776e7f4826d9900369d38fec08ce4622df16df405380b70a3efaf0

Observation f69471e5-12d3-4e0b-a958-4736ecf05449 · outbound

This paper cites and Rokach, L.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion and Rokach, L

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.925942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.925942Z digest=sha256:621069c1641d2827891b7794889419f3c3c46643844c6adda6d8a0a5ec7edccc

Observation c4fd53d7-e6f8-4d6d-83a1-ba9affa3f30e · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.932467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.932467Z digest=sha256:58563163606f8ee87bdb676a41df742b92be9270b3e0b7d9723850905e1d7e38

Observation edc63e12-b8aa-40e6-9daa-cd5e8d8f810d · outbound

This paper cites Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.881199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.937782Z digest=sha256:4a381d7bd0c1e2676e32a105e86f012d7eaad8d62a958441e8c4d88cdc96edce

Observation c8926e3a-6384-42d7-a627-7685154c5687 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 71

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:21.862291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.943449Z digest=sha256:570f0521c5546dae5b80e5f6cc86fe84201c752b4f6953cd335248f4f1dafff0

Observation ae0816ea-6a51-4a09-9bb5-756d17604229 · outbound

This paper cites Linear algebra and its applications.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Linear algebra and its applications

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.842973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.948271Z digest=sha256:b12a8f9dac4a28a979b3b216ac60b4b4c90cd59204ce73f4f2d599e0c80aac2e

Observation 2472283c-a3ab-4e65-ba85-febb78481252 · outbound

This paper cites Optimizing mode connectivity via neuron alignment.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Optimizing mode connectivity via neuron alignment

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.823316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.953672Z digest=sha256:11751857ca1ed7e1534bfabc173a160d44dbdfbb79d0d61473f5ff6bf8c3e4df

Observation f56d2c87-f422-4603-9393-93270cd196e4 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 74

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:21.804484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.959431Z digest=sha256:3bb4b7ea3a0a72a3bed4c63385c396723e1f7c8a00c3ab8e385a67fb88205260

Observation 720cd743-1e63-4de8-b7a9-c37031b01c73 · outbound

This paper cites Equivariant Neural Functional Networks for Transformers.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Equivariant Neural Functional Networks for Transformers

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.965178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.965178Z digest=sha256:90beb75fce8e185dce638abe181e02efc66017e4f1f49c6a2898380fcc84f4ab

Observation 36bacedd-111f-4a17-909b-31968b8dd84c · outbound

This paper cites Least-squares estimation of transformation parameters between two point patterns.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Least-squares estimation of transformation parameters between two point patterns

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.786496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.969673Z digest=sha256:e513fe15dd3652043e3c8579ebeb8cd2b9e74f46bdf2b6af76b6ff524228abed

Observation f3d02690-0c53-489d-8116-2af6612ace53 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion N., Kaiser, ., and Polosukhin, I

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.973985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.973985Z digest=sha256:56a07b0fd8f9c44d4c96c830ac68fa8d1ca282858e062e2d7bdf00b727348f2a

Observation afae7838-30ee-4218-a397-b33c65cd9e17 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 78

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:21.755388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.978236Z digest=sha256:927f292295f86b00cae535231eac7d489ae8ae1b01e1ec142fa14b40ea37965d

Observation e99ea6f3-7a5b-429b-997d-b1a255a741f6 · outbound

This paper cites Federated learning with matched averaging.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Federated learning with matched averaging

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.736288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.982405Z digest=sha256:5a4c774c428a419a691746e3142d0be2a9556550d322b87359d08b25e4e4958c

Observation f06bcd4e-e559-4187-a971-562015a0f505 · outbound

This paper cites Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:20.986905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:20.986905Z digest=sha256:1b9514603b413e1949157922798ce7c143741f96bca35ba2f45d1386f63266fb

Observation 8dc10bf7-aba9-497e-a833-b3db92101ebc · outbound

This paper cites Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.718406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.991209Z digest=sha256:fcaf7fb45a6568b0b9b9a662ef45767c2af781b84481f05e8bcb9a645c337716

Observation 8ee08f16-d49d-4fbc-b897-01736d42c804 · outbound

This paper cites A., and Bansal, M.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion A., and Bansal, M

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.700705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:20.995651Z digest=sha256:04d07e578988eddefcf7d4b784c21a3151359716fd3fbcc27ad5ec98690f850e

Observation ee850eac-1dd0-456a-9cc7-679ce73313e8 · outbound

This paper cites What Matters for Model Merging at Scale?.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion What Matters for Model Merging at Scale?

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:21.000924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:21.000924Z digest=sha256:9f508c5a09b693d613f0e435a5a213350cb42e7f4d6da2ab210475fceedaee26

Observation 2c9c77ce-9f05-4986-81b5-ee7e7beff529 · outbound

This paper cites Adamerging: Adaptive model merging for multi-task learning.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Adamerging: Adaptive model merging for multi-task learning

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.683538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.006554Z digest=sha256:b784b7be02a7fba5d6f1b4b11947f5837e29499017f1b3c87956a54e7ac5d577

Observation bfb6e827-ee3e-45db-a8d1-cc2981376bf1 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:21.012079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:21.012079Z digest=sha256:af1cc19ebff7420e1400e27fb2d12cfacdff80a03af1a01ee3d24b79f351e646

Observation bbfe5df6-fc73-48ba-9276-074d01b8c087 · outbound

This paper cites Bayesian nonparametric federated learning of neural networks.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Bayesian nonparametric federated learning of neural networks

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.654577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.017696Z digest=sha256:3a125fa3068e36b746d1a976960a75a372705ba03d5b6d1a3f6f3c2d67ce746a

Observation 70a08bf3-1d5c-437b-abeb-77264473e109 · outbound

This paper cites Improving Learning to Optimize Using Parameter Symmetries.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Improving Learning to Optimize Using Parameter Symmetries

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:21.029402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:21.029402Z digest=sha256:8378ba2ff6c30c0ad804047d3e61a22aad0643108f151dc7b0122b52d5278244

Observation 03f28ef1-af54-48b2-b067-1a7a3d5fcf06 · outbound

This paper cites Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:21.036373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:21.036373Z digest=sha256:aed21372db380382695675c102cf14ed31c7b1badcdb440e5230ee8f9146e743

Observation cb7f9a1a-9620-4080-9db2-3f892cf68c52 · outbound

This paper cites Symmetry teleportation for accelerated optimization.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Symmetry teleportation for accelerated optimization

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.637323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.041763Z digest=sha256:7f9aa20ca69e965c2d5f10253f181e7148510b6638db05285f00bd77eee1cad0

Observation 98d08a92-c47d-4bcf-a809-7f2d133602ae · outbound

This paper cites Symmetries, flat minima, and the conserved quantities of gradient flow.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Symmetries, flat minima, and the conserved quantities of gradient flow

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.617970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.047025Z digest=sha256:002d2b836ad41fa55b32c0d96de8ba8c20aed04df8c10ffc0c813a5ae9f4f710

Observation b2df3498-708c-4978-9d4f-304f5dfe5c6a · outbound

This paper cites M., Walters, R., and Yu, R.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion M., Walters, R., and Yu, R

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.600381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.053138Z digest=sha256:e8c9e0cdbfeac0971ca669f1dc22e07595e19aa913a447aae45c36d4da20514c

Observation ff369662-499a-4e15-a2b8-2603b7f7024f · outbound

This paper cites Kg-cf: Knowledge graph completion with context filtering under the guidance of large language models.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Kg-cf: Knowledge graph completion with context filtering under the guidance of large language models

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.580366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.059429Z digest=sha256:40474465d45e8083594f8c2005b572a34adf8f290c560e22068f31cf5845bcfe

Observation 545009ac-b744-4f56-8b15-cfdeafe08949 · outbound

This paper cites Z., and Finn, C.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Z., and Finn, C

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.563455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.064279Z digest=sha256:367bcf74609efcf84caab8687f9384875e1c1e558dae6a84aaab7cf2f3d91cab

Observation 185c6655-9073-4723-aaea-2296deaa3f74 · outbound

This paper cites Z., and Finn, C.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Z., and Finn, C

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.547437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.068931Z digest=sha256:42a2a0e32fdb1e5892ceae96ab84beb5bfd3fd0b56ab30b9a2402f602b3b4c9b

Observation 067597fd-4b15-496f-9c0b-d25859eedc3d · outbound

This paper cites Informer: Beyond efficient transformer for long sequence time-series forecasting.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Informer: Beyond efficient transformer for long sequence time-series forecasting

Reference 95

Resolution
unresolved
no resolver link, observed 2026-08-09T19:44:21.073290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:44:21.073290Z digest=sha256:490f43c6f9356b53cf4fb61c5c739ce0d31d8655af8e3cd264165a9b4219c32a

Observation 40ab675f-b508-4d53-bc4b-465568d6ca67 · outbound

This paper cites Metagpt: Merging large language models using model exclusive task arithmetic.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Metagpt: Merging large language models using model exclusive task arithmetic

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.517844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.077411Z digest=sha256:f33e0991b9671e49053b79e935cb8701d65510e687e4511a8740a06bc8aa302b

Observation 6bcdefde-c566-408c-ade8-d30141e4ef8b · outbound

This paper cites Going beyond linear mode connectivity: The layerwise linear feature connectivity.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Going beyond linear mode connectivity: The layerwise linear feature connectivity

Reference 97

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.500599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.082245Z digest=sha256:b0d30eeb90935b078ddb8e8fd29582eff57c32e0838f83f056d679e00f2d144a

Observation 6a64bd47-9210-4357-b495-6616f4bc3ff5 · outbound

This paper cites Understanding and modeling job marketplace with pretrained language models.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Understanding and modeling job marketplace with pretrained language models

Reference 98

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:44:21.483677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.086593Z digest=sha256:635e5d4901b7e16ecda96ab2a9a37fcded8cb52dbf3cc6f485b03c7e04f546c6

Observation 21e6b31d-3a23-4642-a575-be8cb59cc88d · outbound

This paper cites Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent

Reference 99

Resolution
verified exact
local_arxiv, observed 2026-08-09T19:44:21.162695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.092553Z digest=sha256:551c8c2ee1a836b935b5aaaaa8a04faf7c4a2194d224892d0430ba1768f786ad

Observation 4438b30b-57d9-4240-be78-4d459683e9c8 · outbound

This paper cites an unresolved cited work.

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:44:21.466746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-09T19:44:21.097412Z digest=sha256:416c5997f488e9fb31b74e37adfc654fb4209de0921ed485aa0e83041b134ca1

Pith citing papers

Observation 999f6865-8981-4881-994f-036a435c3c1c · inbound

Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing cites this paper.

Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-05T12:34:51.331297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T12:34:51.331297Z digest=sha256:9086e372b016026aeab0ff85a09fdf31d0a6e593e06b6832074ac321ea5ebf76

Observation 36999521-1e43-46e9-be31-df60daa5319b · inbound

Toward Manifest Relationality in Transformers via Symmetry Reduction cites this paper.

Toward Manifest Relationality in Transformers via Symmetry Reduction Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T21:52:35.599649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T21:52:35.599649Z digest=sha256:4ff18e7166ccc5863fba4d0f75fe64ec3891a0627f75000f7ce197bd77002247

Observation 752686b6-30a3-4a13-8832-0cb96d4e8d4e · inbound

Anomalies in Neural Network Field Theory cites this paper.

Anomalies in Neural Network Field Theory Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-13T03:27:12.018657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-13T03:22:19.732529Z digest=sha256:9ec57168c3853bafecada7fc8274eb40a5b32773b9b81aedfe1985b2fdfa6e96

Observation 519922d3-bf63-4a5c-82fb-efba22ea5a52 · inbound

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers cites this paper.

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-07-04T10:39:45.073485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-06-26T08:39:59.835392Z digest=sha256:781f1076c77e0b988f50e673e2d71986033aee520dabfb93f34a9a2f246c4788