Pith. sign in

Paper Citation Record · LEDGER

Revisiting Weight Averaging for Model Merging

As of 19 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 9 inbound Pith citation observations for arXiv:2412.12153.

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

pith.paper-citation-record.v1
2412.12153 v2

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T18:15:59.346606Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:06:07.444962Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T17:28:44.880604Z

Reference resolution

52 of 52 outbound references displayed

  • verified exact0
  • verified fuzzy34
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 17ad4ec4-20cd-4bbf-b5a7-daca02cea2a5 · outbound

This paper cites Multitask learning.

Revisiting Weight Averaging for Model Merging Multitask learning

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.320384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.143450Z digest=sha256:c604bb9845697544351775822531136af22d48029809862d16846dc7ee0fa33b

Observation 04d6ef9b-fa02-4d39-ad64-d1558b67e41b · outbound

This paper cites Remote sens- ing image scene classification: Benchmark and state of the art.

Revisiting Weight Averaging for Model Merging Remote sens- ing image scene classification: Benchmark and state of the art

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.300571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.148083Z digest=sha256:843ca54d383cfa518887cd2fe558c91c27a08dbcbf28b346bfbce35a987ffe4d

Observation f6222379-0a58-40cc-900e-d19dde140f82 · outbound

This paper cites Fusing finetuned models for better pretraining.

Revisiting Weight Averaging for Model Merging Fusing finetuned models for better pretraining

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.152262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.152262Z digest=sha256:233374a41694acdbd926947439a2f29eb253e546826576c6e5281c0c740c28cf

Observation 73f0c2f6-b393-406d-b2f9-bf30af6f4529 · outbound

This paper cites Describing textures in the wild.

Revisiting Weight Averaging for Model Merging Describing textures in the wild

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.156801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.156801Z digest=sha256:ddacf530b8c3f480c5fd21bce0128c8419e66f2e9d6e3feb61348400e91a197c

Observation 64245187-fe8e-472a-8557-e57122ab14a6 · outbound

This paper cites Deep learn- ing for classical japanese literature, 2018.

Revisiting Weight Averaging for Model Merging Deep learn- ing for classical japanese literature, 2018

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.254290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.161116Z digest=sha256:25338c0e6056df37c94998b848691bf91143b1cf8568f45670fbafc44adca0ca

Observation e4a5d2b0-8182-4e49-b268-6ea8ec22501e · outbound

This paper cites An analysis of single-layer networks in unsupervised feature learning.

Revisiting Weight Averaging for Model Merging An analysis of single-layer networks in unsupervised feature learning

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.225983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.166060Z digest=sha256:3472a86822f45117e6cbeaeaf0d1499877abd3edacb51974241e3dd420a9a810

Observation 0cbbf427-472a-4005-8b8d-3edf8b2af7e5 · outbound

This paper cites Emnist: Extending mnist to handwritten letters.

Revisiting Weight Averaging for Model Merging Emnist: Extending mnist to handwritten letters

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.208663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.173513Z digest=sha256:90cc4fdde2bdc3c01d6fd4f4905f7000246d271b43d485a8a7f9b5c8ed928a5d

Observation 8450ef9a-5d3d-4992-b1cc-4ffc925fc5c4 · outbound

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

Revisiting Weight Averaging for Model Merging An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.177933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.177933Z digest=sha256:67abdd2bf4ad34543d5f727086bbeaeab61550d14bb808bae5c4bd16aa4649e0

Observation 116fbf5e-873f-4d54-991f-e5381386d589 · outbound

This paper cites Essentially no barriers in neural network energy landscape.

Revisiting Weight Averaging for Model Merging Essentially no barriers in neural network energy landscape

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.174593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.181755Z digest=sha256:e9431b4b25f70a1328d0bff49d7b90cc257dfe98b55cf4fb20bf9860e7d756f4

Observation 1e2a32d1-dd50-4ecc-bc9a-ef46beb610b6 · outbound

This paper cites Linear mode connectivity and the lot- tery ticket hypothesis.

Revisiting Weight Averaging for Model Merging Linear mode connectivity and the lot- tery ticket hypothesis

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.152545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.185532Z digest=sha256:27767b6301a8dd096e3c2703e5bbe0ffad14a2303baedb3abf29f9d892114e10

Observation 973ba31a-7554-48cf-94f7-e64830a4e471 · outbound

This paper cites Task Singular Vectors: Reducing Task Interference in Model Merging.

Revisiting Weight Averaging for Model Merging Task Singular Vectors: Reducing Task Interference in Model Merging

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.190300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.190300Z digest=sha256:da3b99ee7de2ba29fa757b9a459d1a6c807a4cd8d458fd8cb823ce1b0ffdbf80

Observation 40f4e27d-e994-4b02-92d9-b82191d1fd91 · outbound

This paper cites Loss surfaces, mode connectivity, and fast ensembling of dnns.

Revisiting Weight Averaging for Model Merging Loss surfaces, mode connectivity, and fast ensembling of dnns

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.126356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.194987Z digest=sha256:4cf9d61951601091d8044b850bd72b4441423e7d6ac6f3d9f4f47f62131d92b5

Observation ac1ac418-4cf6-4236-a9d3-75f5d3795ab7 · outbound

This paper cites Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification.

Revisiting Weight Averaging for Model Merging Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.198873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.198873Z digest=sha256:d2ff9067ee422d20b3e1b36c2461df300d5646f0834063c784dfbb80ea0f781a

Observation 67054500-8a48-4c95-8179-d4e2f9fa3b65 · outbound

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

Revisiting Weight Averaging for Model Merging Emr-merging: Tuning-free high- performance model merging

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.096600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.203239Z digest=sha256:c5e2ff6aa5dadce40595de8e1c304106d2f0f32fab44bdb8c0f3e34b76c3bbd3

Observation bd295c74-2efc-4942-bcd7-8a0b14a783c8 · outbound

This paper cites Patching open-vocabulary models by interpolating weights.

Revisiting Weight Averaging for Model Merging Patching open-vocabulary models by interpolating weights

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.073819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.207726Z digest=sha256:e2cf602ade746996875dc4ea20c1e5d8aa2c6390e23b15058e3bb71d48df4fb8

Observation b985e591-bc72-40c7-a3bd-a40b1c2bddcb · outbound

This paper cites Patching open-vocabulary models by interpolating weights.

Revisiting Weight Averaging for Model Merging Patching open-vocabulary models by interpolating weights

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.047205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.211695Z digest=sha256:e32aff520912dd29a1b80d0ee3117596a4fc6547c0eb876981c61ee8aef6395a

Observation d68bc39d-de8e-40a1-8fec-6aad7cc7c964 · outbound

This paper cites Editing models with task arithmetic.

Revisiting Weight Averaging for Model Merging Editing models with task arithmetic

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.027242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.216491Z digest=sha256:7279d474abd543d78bb00b9c85ae51a76570ba150589227b025643cac7f7b7bc

Observation 6546b549-0104-4842-9592-59fe61b28074 · outbound

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

Revisiting Weight Averaging for Model Merging Dataless knowledge fusion by merging weights of language models

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:16:00.002571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.221196Z digest=sha256:45b1a169743cf83681e7d530f8042c44a092fb5f64a768aadb7358a3c24682be

Observation 504788f6-40b5-4364-9588-9faaa918fe6b · outbound

This paper cites Combining Weakly and Webly Supervised Learning for Classifying Food Images.

Revisiting Weight Averaging for Model Merging Combining Weakly and Webly Supervised Learning for Classifying Food Images

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.225268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.225268Z digest=sha256:ed323b80ac9924becc6274d884155fbaa2f6274e3bdca95c142396c842d61b9a

Observation 98782c59-c869-4b32-aa99-3900c4552b11 · outbound

This paper cites Facial Emotion Recognition: State of the Art Performance on FER2013.

Revisiting Weight Averaging for Model Merging Facial Emotion Recognition: State of the Art Performance on FER2013

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.229122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.229122Z digest=sha256:a83df2b2d70db2cdd2dc789453f5b143baa01923dbddf662a2eaef4f12222ec8

Observation 26aa73d4-b0ee-4cec-a347-943a4345c8b0 · outbound

This paper cites 3d object representations for fine-grained categorization.

Revisiting Weight Averaging for Model Merging 3d object representations for fine-grained categorization

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.232777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.232777Z digest=sha256:36ae21b531ba0b1a8403afc6b103c82b39e6b83c3047b82bfc116966ec524c9b

Observation 9e17a42b-2055-4649-a080-4349ba5f4f1e · outbound

This paper cites Learning multiple layers of features from tiny images.(2009), 2009.

Revisiting Weight Averaging for Model Merging Learning multiple layers of features from tiny images.(2009), 2009

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.972547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.236427Z digest=sha256:9dfab333b555ffd00becd87a63d5869731094bfabe7833bfb2b4658a88e2652c

Observation bd0bb85e-dd7a-41af-a81c-95754453f125 · outbound

This paper cites The mnist database of handwritten digits.

Revisiting Weight Averaging for Model Merging The mnist database of handwritten digits

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.240469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.240469Z digest=sha256:812eab3f90103fe289c8c7142eaedf61cd7bc178f121a10f9f477741d73b4f1e

Observation 81cbb466-6310-405c-916a-537bb1a15498 · outbound

This paper cites Visualizing the loss landscape of neural nets.

Revisiting Weight Averaging for Model Merging Visualizing the loss landscape of neural nets

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.934433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.243877Z digest=sha256:bb3c97be9189fea3a028987f7c3b99fabdb4595566a4d23b2f63dc927d251801

Observation 79a550f3-0f39-42f0-8e0f-61970b43032c · outbound

This paper cites Visualizing the loss landscape of neural nets.

Revisiting Weight Averaging for Model Merging Visualizing the loss landscape of neural nets

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.917441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.247207Z digest=sha256:014be310858fac0afc774eea68a5a5e1c2ed0ac5847fda2ecff97b5eb25d10fe

Observation a3824b06-fa0c-46ed-b128-86bdcad018d0 · outbound

This paper cites Deep Model Fusion: A Survey.

Revisiting Weight Averaging for Model Merging Deep Model Fusion: A Survey

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.251829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.251829Z digest=sha256:fbf7002dab67099f3a011309c598f77032e0e66a2d543b0799f771379e55a9f7

Observation 50476ed6-5866-4af1-9d26-a74de3decfb2 · outbound

This paper cites Conflict-averse gradient descent for multi-task learn- 9 ing.

Revisiting Weight Averaging for Model Merging Conflict-averse gradient descent for multi-task learn- 9 ing

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.902103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.256018Z digest=sha256:1bae7cf4ca17c5d608097185d76367e852575da9ba65b156adf449cfe06f6f14

Observation c513b67c-dd4e-4dda-bad4-8776773093c7 · outbound

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

Revisiting Weight Averaging for Model Merging RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.259355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.259355Z digest=sha256:b415bbaf54f4bd72ef81ab5c3f5d05bb597a9c940df22a4245b80d0e2bb591ab

Observation 3892c428-54fa-4784-b4ab-1e03220c321f · outbound

This paper cites Magmax: Leveraging model merging for seamless continual learning.

Revisiting Weight Averaging for Model Merging Magmax: Leveraging model merging for seamless continual learning

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.888286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.263333Z digest=sha256:7d441f2d1fe3007f9f49e751ef02a7c627b7128651193f1b60a25112adcae197

Observation bf234bf8-2497-429a-ade1-859d1769cafa · outbound

This paper cites Merging models with fisher-weighted averaging.

Revisiting Weight Averaging for Model Merging Merging models with fisher-weighted averaging

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.874441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.267297Z digest=sha256:d38b1f51d27b68ca804a2e3817824d76d35f5e931be76263546bf389c3f1de91

Observation 3d06bd06-b56a-4a08-ada6-cad6e66d6fff · outbound

This paper cites Deep double descent: Where bigger models and more data hurt.

Revisiting Weight Averaging for Model Merging Deep double descent: Where bigger models and more data hurt

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.858178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.271547Z digest=sha256:291b0b19b350afcd9667102e87b158870505fe52c26ac89124b823fc792c6b25

Observation 760b47c0-f3b3-4f8b-b0c8-f3026b19ddd3 · outbound

This paper cites Reading digits in natural images with unsupervised feature learning.

Revisiting Weight Averaging for Model Merging Reading digits in natural images with unsupervised feature learning

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.274936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.274936Z digest=sha256:7afaf0069df8c5dea2e5eb225972be4362e8f488e15ce16190951d385fc5a908

Observation 446e9c38-67fe-4231-99ef-420f43094b70 · outbound

This paper cites What is being transferred in transfer learning? Advances in neural information processing systems, 33:512–523, 2020.

Revisiting Weight Averaging for Model Merging What is being transferred in transfer learning? Advances in neural information processing systems, 33:512–523, 2020

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.822348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.278809Z digest=sha256:e3c84149efb571e2f692c329e473634dbe9482724a76c0a0be38793198373ff8

Observation 2dfd05b5-52fe-4dfc-8e7b-88ef221e74d3 · outbound

This paper cites Automated flower classification over a large number of classes.

Revisiting Weight Averaging for Model Merging Automated flower classification over a large number of classes

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.282195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.282195Z digest=sha256:1753e8e131886d640582a681ae5d9388b2e0f8f31ca22c2c59e1653072557a31

Observation 8339a4c6-4cfe-41a2-bf1b-2e9663d307fe · outbound

This paper cites Task arithmetic in the tangent space: Improved editing of pre-trained models.

Revisiting Weight Averaging for Model Merging Task arithmetic in the tangent space: Improved editing of pre-trained models

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.790086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.285534Z digest=sha256:e91d1e8e437bc1e376c1f405882f0a113222d5b73d73943a2acd58ce20b2f622

Observation 66677908-f5db-4c70-a2a0-2f10f7755241 · outbound

This paper cites Cats and dogs.

Revisiting Weight Averaging for Model Merging Cats and dogs

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.289079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.289079Z digest=sha256:52a3ad6287a934e447b1c29a46da6838efe19834863a6ef448e8902cb157688b

Observation c4452b9a-f379-4adb-a38b-061ae1e014fd · outbound

This paper cites Model aggregation techniques in federated learning: A comprehensive survey.

Revisiting Weight Averaging for Model Merging Model aggregation techniques in federated learning: A comprehensive survey

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.750668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.292401Z digest=sha256:452f50bef4f587d37437f8a773075065a82fb1680d7886b929a7616dbf729d08

Observation a24ece2f-e714-4563-a916-f5f54cea3f38 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Revisiting Weight Averaging for Model Merging Learn- ing transferable visual models from natural language super- vision

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.732434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.295872Z digest=sha256:9e10ff0671a5ecb82e945c2cdffb453ea44505bfb25c2fe188c0fd61bd4e7f9c

Observation 129c9a38-83ac-47b1-a841-b5c689687b0b · outbound

This paper cites Multi-task learning as multi-objective optimization.

Revisiting Weight Averaging for Model Merging Multi-task learning as multi-objective optimization

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.299056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.299056Z digest=sha256:37696eea2117a2459b783dfe953e6db67fa4cb90653af6450ecec7d90b0518d1

Observation 34aff9d6-fc15-48c5-b990-b981b9ba0872 · outbound

This paper cites Model fusion via opti- mal transport.

Revisiting Weight Averaging for Model Merging Model fusion via opti- mal transport

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.701128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.303016Z digest=sha256:2ed9b6e6098bdc86f604f2dad6f78bbfeac00bdd39ed6fad680fe847d5e05240

Observation 271a17d6-c4fc-428a-a7f1-c6371f16c661 · outbound

This paper cites Manning, Andrew Ng, and Christopher Potts.

Revisiting Weight Averaging for Model Merging Manning, Andrew Ng, and Christopher Potts

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.685790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.306346Z digest=sha256:88e3707a89e3c1b6685906a288d0d7187f9d51a57f0099b2a3618f367c0c80b4

Observation 410988e6-611c-47a6-b8ff-76aa60a20c60 · outbound

This paper cites The german traffic sign recognition bench- mark: a multi-class classification competition.

Revisiting Weight Averaging for Model Merging The german traffic sign recognition bench- mark: a multi-class classification competition

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.670705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.309714Z digest=sha256:af8fa92b86999b6d290b78d2d04cc5a633de75ecddb5a0d074ff5ded486f0216

Observation b2853cb4-c570-4b1c-bf05-a972a6865090 · outbound

This paper cites Rotation equivariant cnns for digital pathology.

Revisiting Weight Averaging for Model Merging Rotation equivariant cnns for digital pathology

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.653262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.312926Z digest=sha256:4418d9d491bb581a4241b4f3a7298847dd15b6e3cd000aa73eaeb0acaf8225f7

Observation 78df2362-877b-44f2-9782-b96169109b28 · outbound

This paper cites Machine Learning Model Sizes and the Parameter Gap.

Revisiting Weight Averaging for Model Merging Machine Learning Model Sizes and the Parameter Gap

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.316304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.316304Z digest=sha256:4fff2de133a868fac5bfbad47f398009968aafa2cd7b0f0959c768e83a619fe2

Observation cdae4f30-e41f-4992-85d6-9ccced5b477f · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

Revisiting Weight Averaging for Model Merging GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.320681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.320681Z digest=sha256:04ce93a41548e61d7b82eb203a2c5ee1a9dd7efbc647ce592d91097447ea2a61

Observation fd29a743-5971-4c22-b13d-060c3186c572 · outbound

This paper cites Tent: Fully Test-time Adaptation by Entropy Minimization.

Revisiting Weight Averaging for Model Merging Tent: Fully Test-time Adaptation by Entropy Minimization

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-11T18:15:59.325045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T18:15:59.325045Z digest=sha256:e7fbae72105541b71d3f86a9c4dff011ebe52995c5090d5b042aea9d7a31fc72

Observation db3ecb9a-8e25-46e4-aca3-dc14d00636bd · outbound

This paper cites Localizing task in- formation for improved model merging and compression.

Revisiting Weight Averaging for Model Merging Localizing task in- formation for improved model merging and compression

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.640277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.328908Z digest=sha256:0b197d83c23642ad9759ec21643acd54a0f09292e97c6332fde40975bbd07d0e

Observation 65634a83-a724-415c-9288-ae3e873ec548 · outbound

This paper cites Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing in- ference time.

Revisiting Weight Averaging for Model Merging Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing in- ference time

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.625180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.332640Z digest=sha256:17370d47606e11f8872bd1db2cad69e457bbf1ddd4ce973855e88ac20ec5f73b

Observation 412b38c5-3978-488b-b0c0-88099f5864f3 · outbound

This paper cites Fashion- mnist: a novel image dataset for benchmarking machine learning algorithms, 2017.

Revisiting Weight Averaging for Model Merging Fashion- mnist: a novel image dataset for benchmarking machine learning algorithms, 2017

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.609303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.336377Z digest=sha256:1ad79efe44790fb9d5b7c4f49ba1a2dbf65d30ca2d65aa2931685ff7049a806f

Observation 4abdadc9-03c9-4369-99fa-30b47d57f0c7 · outbound

This paper cites Sun database: Exploring a large col- lection of scene categories.

Revisiting Weight Averaging for Model Merging Sun database: Exploring a large col- lection of scene categories

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.594179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.339434Z digest=sha256:cbb7e3fd244bd6e5d605cf578f8e787c6ce0ed386ac3260eca759f175e82f476

Observation 14a804ed-fabb-4e9e-8389-bbd53a544dcc · outbound

This paper cites Ties-merging: Resolving interference when merging models.

Revisiting Weight Averaging for Model Merging Ties-merging: Resolving interference when merging models

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.575964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.343029Z digest=sha256:84fe2ed517f4b84f29582a99c32b2f99cf2d88a5bb7a201a332e6e71545783f7

Observation a404867c-476b-4fae-8e8e-620e95b09f8f · outbound

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

Revisiting Weight Averaging for Model Merging Adamerging: Adap- tive model merging for multi-task learning

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T18:15:59.561287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-11T18:15:59.346606Z digest=sha256:a1cbd2a86343039ed768c2b31363005828bc762fb8bed63847ea10b1f1ad6815

Pith citing papers

Observation 83f4cbe2-f058-4aec-9c32-88f657741e70 · inbound

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent cites this paper.

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent Revisiting Weight Averaging for Model Merging

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-10T22:38:48.706611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:38:48.706611Z digest=sha256:ae735ca959fc285cc69bc011c46670dfed2aa30536579623c0a2d6e0e01b2161

Observation d265a83f-900c-46d6-ba8d-a30de0a616bc · inbound

Why Do More Experts Fail? A Theoretical Analysis of Model Merging cites this paper.

Why Do More Experts Fail? A Theoretical Analysis of Model Merging Revisiting Weight Averaging for Model Merging

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T13:44:32.908553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:44:32.908553Z digest=sha256:c88c705ef8fadd72a337e4fa08ae91573fd3f9d4938781590ae5217b14fe2d26

Observation ceb78608-36ca-4041-b0c3-f9ae6248e627 · inbound

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning cites this paper.

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning Revisiting Weight Averaging for Model Merging

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-15T19:06:07.444962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T19:06:07.444962Z digest=sha256:e4118108f567719dc84a32e722c53eeccc1818f4536ae4079e34a3265a5b49b3

Observation 89844575-7a88-44a1-8348-e9f38709dc7a · inbound

ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation cites this paper.

ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation Revisiting Weight Averaging for Model Merging

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-15T17:00:10.099140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-15T16:58:36.575824Z digest=sha256:b3d9ac55aabd1d2b896ab80404802e18643c8b9802634660baca1a3dae81883f

Observation 3e4e6f8d-00b6-4d37-b2ca-2e00e76b03b5 · inbound

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks cites this paper.

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks Revisiting Weight Averaging for Model Merging

Reference 9

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T11:26:02.244440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-10T14:56:04.775995Z digest=sha256:a16af043ec68eca71fa62c406ec5a3f8afa68f51d8880f36e062e6740108c74a

Observation b33b4381-a21b-4d9f-a8ff-c65b30f173bc · inbound

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks cites this paper.

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks Revisiting Weight Averaging for Model Merging

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T16:19:20.411848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T16:19:20.411848Z digest=sha256:b3f5ae0bf0aaf19d065ea29a42dc80f63e330a61fd2f6ad1db64bf964770354b

Observation c8f50cc7-150a-4a50-b7f0-ad2d397514e0 · inbound

Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration? cites this paper.

Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration? Revisiting Weight Averaging for Model Merging

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-13T00:15:58.111384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T00:15:58.111384Z digest=sha256:568ebb1c3e8b793a30686c70f732641719a2a0a558d724d193dec31337960b02

Observation 6b384b8c-8f2c-4387-a5ee-9ffaf484b6e7 · inbound

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter cites this paper.

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter Revisiting Weight Averaging for Model Merging

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-07-02T01:56:27.696273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-28T11:24:45.010310Z digest=sha256:b9ae43adb1088a3a2554c12dd7881c4d92c5e5b90073aad1d508837f680887c7

Observation 0ac461bd-8500-444a-a8da-83c1fb81cf77 · inbound

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI cites this paper.

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI Revisiting Weight Averaging for Model Merging

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-07-03T17:28:44.882031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-27T04:02:53.110012Z digest=sha256:27816d7aed5a180392757060a727b5979fc752e4cbe4a1ffca178e0e35b81eef