Pith. sign in

Paper Citation Record · LEDGER

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

As of 19 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2505.15133.

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

pith.paper-citation-record.v1
2505.15133 v1

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:27:41.962913Z

measured 54 of 54 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

54 of 54 outbound references displayed

  • verified exact0
  • verified fuzzy37
  • unresolved17
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e0d404fe-84a1-4882-bc5f-aa7ea4bf6621 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Distilling the Knowledge in a Neural Network

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:36.503841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:36.503841Z digest=sha256:eae486d93d765eea0ed86750eb0d611d20eddca95954f1308c36f3045d322bec

Observation 64b2b912-3b68-4659-89e3-4725851ac93f · outbound

This paper cites Pkd: General distillation framework for object detectors via pearson correlation coefficient,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Pkd: General distillation framework for object detectors via pearson correlation coefficient,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:46.663089Z

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=2026-08-07T15:27:36.578218Z digest=sha256:71554c6596fef47fc4002e15440b66b9724f585d86497f7f96ac65e68163fe11

Observation 467201bb-2142-498f-b62a-937a8ad9c233 · outbound

This paper cites Cross-image relational knowledge distillation for semantic segmentation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Cross-image relational knowledge distillation for semantic segmentation,

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:46.492888Z

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=2026-08-07T15:27:36.654784Z digest=sha256:66d09a9ebb049285697fa2734046d1a10b042d45467be67936074c3e82bb3554

Observation 048105f7-9498-482e-92b3-a565ffb73c11 · outbound

This paper cites Relational diffusion distillation for efficient image generation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Relational diffusion distillation for efficient image generation,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:46.383344Z

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=2026-08-07T15:27:36.732477Z digest=sha256:6c3b396c3454d56bf138140f628439db7105f7db67f189bfbc26a39cca9a91a3

Observation 5092153c-9184-4b2f-8096-1e0113b51c65 · outbound

This paper cites Knowledge distillation: A survey,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Knowledge distillation: A survey,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:36.856590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:36.856590Z digest=sha256:fff97a33cadf315c2633d1e996b5cbb65d4fa38066b4607888c744773df55445

Observation 41b20559-7d8e-479e-a778-ad088e418074 · outbound

This paper cites Knowledge distillation from single-task teachers to multi-task student for end-to-end au- tonomous driving,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Knowledge distillation from single-task teachers to multi-task student for end-to-end au- tonomous driving,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:46.217421Z

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=2026-08-07T15:27:36.954959Z digest=sha256:7c55b2f4cb37562d6fa28a29181335b147df25804a3d0e024ec9ae72b6322946

Observation b5d56058-ea41-4dab-81a0-663b44a4f22f · outbound

This paper cites Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:37.033544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:37.033544Z digest=sha256:01b2aa2d41cf80bafbc4c78a418358e6fe96cea2a1f65e72f469dd1557c6a6bc

Observation 87b6d3ed-9c3b-4d10-ac30-0637744beb7c · outbound

This paper cites MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:37.106377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:37.106377Z digest=sha256:668166ec3fc208a29955441cd112b03707ac41e1585fb28469dfef98f79a30b9

Observation 6166566b-e677-426c-9f83-500f7b089d71 · outbound

This paper cites Adaptive multi-teacher knowledge distillation with meta-learning,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Adaptive multi-teacher knowledge distillation with meta-learning,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:46.092176Z

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=2026-08-07T15:27:37.182448Z digest=sha256:c5549ddfd31fce43ef020dc5c4a89d460ac730356740cf6923bda98176127e6d

Observation f1a44d36-16d0-46d4-9421-234512dbad1f · outbound

This paper cites Multi-teacher knowledge distillation with reinforcement learning for visual recognition,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Multi-teacher knowledge distillation with reinforcement learning for visual recognition,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.996742Z

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=2026-08-07T15:27:37.261794Z digest=sha256:920a871d7ab7d2f8275bede523d3a6471005af0ec9159b505c81b447e4eaa053

Observation 6608e0ae-61ac-461a-b50f-01971e9db70f · outbound

This paper cites A comprehensive overhaul of feature distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer A comprehensive overhaul of feature distillation,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.912751Z

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=2026-08-07T15:27:37.354357Z digest=sha256:5b90258c8eb49b31427a3666c56a411688954cee80ddee67e38d1229d8e75dc3

Observation b792ffef-1906-4fcb-bad1-7f0d4f376713 · outbound

This paper cites What makes a.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer What makes a

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.733883Z

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=2026-08-07T15:27:37.459039Z digest=sha256:c197b8315a4e4d54014eb9c1be08c9e84f9bee2fdcf8695707a1954ac60432c9

Observation 6399e879-f0b9-4fcb-b5dd-14a752be7a78 · outbound

This paper cites Cross-view consistency regularisation for knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Cross-view consistency regularisation for knowledge distillation,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.553511Z

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=2026-08-07T15:27:37.532823Z digest=sha256:dbc06cf0152ee64c14a2e850d96b168dd84af69520e933f2a02fee3bdab3b8c5

Observation d032f3f7-5560-4133-8105-236682a551ad · outbound

This paper cites Why logit distillation works: A novel knowledge distillation technique by deriving target augmentation and logits distortion,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Why logit distillation works: A novel knowledge distillation technique by deriving target augmentation and logits distortion,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.448812Z

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=2026-08-07T15:27:37.623360Z digest=sha256:92c25e7d774fec1b0464f82aa075c4fac659ec1f431481c8478e7abcf785eddd

Observation ca360851-f8b1-4ea1-adf6-5a265f7dadd9 · outbound

This paper cites Single teacher, multiple perspectives: Teacher knowledge augmentation for enhanced knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Single teacher, multiple perspectives: Teacher knowledge augmentation for enhanced knowledge distillation,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.271202Z

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=2026-08-07T15:27:37.724296Z digest=sha256:e0bb69a785a0f174ed3d410830f33bb0da588d10b6fb46aca6beef0c12a86cd4

Observation c0201d6e-27ff-4f44-b48d-3af497d56479 · outbound

This paper cites Revisiting knowledge distillation via label smoothing regularization,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Revisiting knowledge distillation via label smoothing regularization,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.174276Z

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=2026-08-07T15:27:37.806925Z digest=sha256:7cb06a053732c62e646dc87c947765c1ba3aa4e46ac653c3d4c74f8b635394b9

Observation 63ba9aac-2e8f-4535-9ab1-63c20a700ab0 · outbound

This paper cites Debiased distillation for consistency regularization,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Debiased distillation for consistency regularization,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:45.010488Z

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=2026-08-07T15:27:37.893043Z digest=sha256:a54f8e972573580490093692d236d263fee1566121634ed02a1650359c4ad7fa

Observation ac41c58b-b66a-496b-9ce1-85c355043b37 · outbound

This paper cites Decoupled knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Decoupled knowledge distillation,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:37.975545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:37.975545Z digest=sha256:9c72806aea9874f0b6c1d857d8dc01c837621445269c83ae5bd3b1c733cd2753

Observation 6397544c-5d4c-460d-b1f0-97864a93412a · outbound

This paper cites Dot: A distillation-oriented trainer,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Dot: A distillation-oriented trainer,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.924995Z

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=2026-08-07T15:27:38.097181Z digest=sha256:b3dc4b34abb2b58d4469161132a9783ce8d4957760be4f7d900a4cc608f822d4

Observation 88a4b7fa-7ffe-4c10-89c5-3a9e18616648 · outbound

This paper cites Medhi, Stochastic processes.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Medhi, Stochastic processes

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.770014Z

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=2026-08-07T15:27:38.183381Z digest=sha256:b767d29429d3c03fc2472b9bc910b07653fbe3fc7aa79c5c1d00fa1398898126

Observation 61a9c61d-76fa-4573-b50b-969855e3b1e8 · outbound

This paper cites Understanding Why Neural Networks Generalize Well Through GSNR of Parameters.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:38.291896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:38.291896Z digest=sha256:93915b17ccc3ef64f78f315e9ec7afac8361f2f1918728b7c6569ba813b26da7

Observation 12ca687c-de2b-400b-92d1-d57d5b2d29b7 · outbound

This paper cites Towards understanding how momentum improves generalization in deep learning,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Towards understanding how momentum improves generalization in deep learning,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.684333Z

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=2026-08-07T15:27:38.372172Z digest=sha256:277cc6be8ca7f5aa565239f07529f3359018d7b06a43b0693c70fff8caa727e8

Observation e7d7e849-6faf-432d-8b4b-3ab51de783b8 · outbound

This paper cites Visualizing the loss landscape of neural nets,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Visualizing the loss landscape of neural nets,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.516004Z

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=2026-08-07T15:27:38.452250Z digest=sha256:32a8fd1ed35a6f6ed7605f7db797c8c683710ed21cfa6f46ef3d6ad291fcce5f

Observation 04c92e22-e759-4f8e-9f62-40a26f7b97a2 · outbound

This paper cites Tighter variational bounds are not necessarily better,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Tighter variational bounds are not necessarily better,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.422216Z

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=2026-08-07T15:27:38.562746Z digest=sha256:d0d25fd8f799f0be9bca7e153863f016c9eb8011872eca0311996d6b8e4a1c53

Observation 6da10cd4-e92a-464c-b70a-efd994502bdc · outbound

This paper cites On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:38.643965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:38.643965Z digest=sha256:c5d93a3d28a55945cbe86b6f86c10cbdd3a7f68bb99d50514557555c32234037

Observation 5afee9b5-69c2-40db-9483-4f2cb568233f · outbound

This paper cites Averaging Weights Leads to Wider Optima and Better Generalization.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Averaging Weights Leads to Wider Optima and Better Generalization

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:38.742449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:38.742449Z digest=sha256:2cd6bf26cdf261e4a038ae0adc7f0f1a53820704c99f5eda014aafcf05168ded

Observation f5091cf0-be73-4ccf-bcaf-f3443446fc1c · outbound

This paper cites Curriculum learning,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Curriculum learning,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:38.796907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:38.796907Z digest=sha256:f0158ad5f7d81a6c1076eab9f5ec914c9915b0efd81c0c8421017bea990724fa

Observation 24e1d452-a394-4b57-9a9b-0e5825fd2bba · outbound

This paper cites Curriculum temperature for knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Curriculum temperature for knowledge distillation,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.251571Z

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=2026-08-07T15:27:38.919632Z digest=sha256:3706170f9f8a05dbc05616449e6138533bbc48da0b4fce13273396112cee25a6

Observation c3a8e71d-4001-4eae-9d9b-84fe6d0e6c0f · outbound

This paper cites Improving knowledge distillation via head and tail categories,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Improving knowledge distillation via head and tail categories,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.147153Z

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=2026-08-07T15:27:39.021002Z digest=sha256:7ba8ef6ebcc91c1de492479f054902f04e3a9b736415be3a781c290f2d5158c9

Observation 81c3a00c-306c-4316-b095-7ac8416df457 · outbound

This paper cites FitNets: Hints for Thin Deep Nets.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer FitNets: Hints for Thin Deep Nets

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:39.103516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:39.103516Z digest=sha256:380cbadb2d918a926daee2f3a3827a7e998d7e089e8baa85998c7c43e08e2a97

Observation 3a78a949-c106-4b62-815a-c464be8542d5 · outbound

This paper cites From knowledge distillation to self-knowledge distillation: A unified approach with normalized loss and customized soft labels,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer From knowledge distillation to self-knowledge distillation: A unified approach with normalized loss and customized soft labels,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.913091Z

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=2026-08-07T15:27:39.485521Z digest=sha256:611e2156addb2883045a1b0bbbfbe744cc9d03bc38cbd6002f8b495816df25cc

Observation d62e952e-6251-41cf-878c-757fde8dec17 · outbound

This paper cites Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:39.597718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:39.597718Z digest=sha256:3580840ee36c15b3e2a49150e21f963bffd0f1b8e1de24a63c8257071a5d3fe0

Observation 67eb321e-2747-41ad-aa17-bfc5e4ce8bb5 · outbound

This paper cites Mdr: Multi-stage decoupled relational knowledge distillation with adaptive stage selection,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Mdr: Multi-stage decoupled relational knowledge distillation with adaptive stage selection,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.774648Z

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=2026-08-07T15:27:39.716428Z digest=sha256:c9764899453957d3f3893cc147c35127d098eb3c5897875c950f32f0acbe4a67

Observation d5dc53a5-1c2b-492d-842c-c2f633ac00a7 · outbound

This paper cites Ntce-kd: Non-target-class-enhanced knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Ntce-kd: Non-target-class-enhanced knowledge distillation,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.669628Z

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=2026-08-07T15:27:39.795288Z digest=sha256:456cfd5d64cfe2e82a8410226bac175a9c9a1a124d51fa1702bdc4dbcec64177

Observation d2f9a4b5-dbe6-4d8c-b83c-5845dfaa0bb4 · outbound

This paper cites Teach less, learn more: On the undistillable classes in knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Teach less, learn more: On the undistillable classes in knowledge distillation,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.554923Z

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=2026-08-07T15:27:39.874730Z digest=sha256:ce2c5f714c6ac978ec3cc44b28a3b02aa61e1c1bd4b931c45ff49eb82f0d2cfb

Observation 3764e83b-aff0-4d4a-9bd1-e7eb7eb6d295 · outbound

This paper cites Knowledge Distillation with Refined Logits.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Knowledge Distillation with Refined Logits

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:39.980502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:39.980502Z digest=sha256:f3e44375d7dbd627582b83dd0388c9ba927a598271aa6664c656b20a674cf0e6

Observation af30dbb8-8622-40bb-a948-fa405798e00a · outbound

This paper cites Domain generalization guided by gradient signal to noise ratio of parameters,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Domain generalization guided by gradient signal to noise ratio of parameters,

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.449455Z

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=2026-08-07T15:27:40.074252Z digest=sha256:cb36db486a628c8f9ac0f54ca9237830c50312e1a7c4344757e561de33485bf9

Observation e2ea07f6-45e4-46f9-a864-dd2202ede79e · outbound

This paper cites On the importance of initialization and momentum in deep learning,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer On the importance of initialization and momentum in deep learning,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.332392Z

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=2026-08-07T15:27:40.179286Z digest=sha256:ca99af080f4724aaf9011f9be13dff3fdb957298f2245d0085ea061978a0853d

Observation a1ec5fe2-5abf-4729-b67e-2050f1fe33da · outbound

This paper cites Adam: A Method for Stochastic Optimization.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Adam: A Method for Stochastic Optimization

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:40.246422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:40.246422Z digest=sha256:093cc854324103efafb7972312a8c8bbec0c581b4e21d5660836f179522d9d6b

Observation d69f7d98-70f0-4dab-8bc1-e997aa6b81c6 · outbound

This paper cites Training data-efficient image transformers & distillation through attention,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Training data-efficient image transformers & distillation through attention,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.224578Z

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=2026-08-07T15:27:40.299744Z digest=sha256:e695b747e7c7813d5bb39f5aa21f6481316b2201bcecd5e965ad81140b162d66

Observation bf2ac38d-8b05-43ea-8c90-8b6dd8a6a301 · outbound

This paper cites Logit standardization in knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Logit standardization in knowledge distillation,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.130329Z

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=2026-08-07T15:27:40.439946Z digest=sha256:984c7171ffe7cebb031af828c231b2f6b1c8f014103b2e0a48262cb53fb6f6e5

Observation aec4fc97-6318-45a5-a673-7d6192ad26dc · outbound

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

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Learning multiple layers of features from tiny images,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:40.599509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:40.599509Z digest=sha256:12a1cc992076dad478f73beb432cf9dc8113b942c87672caf48a87c7e7d71f8c

Observation 1fdf1eb6-8e30-4f23-b400-e44c51576af0 · outbound

This paper cites ImageNet large scale visual recognition challenge,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer ImageNet large scale visual recognition challenge,

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:43.016295Z

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=2026-08-07T15:27:40.736777Z digest=sha256:783399a0c511fc3c8ababedf6620aa645afd6fe034104091a1aca33c68c5c3c1

Observation faaeaf93-e5fb-4ba9-a74f-ed0458292694 · outbound

This paper cites Microsoft coco: Common objects in context,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Microsoft coco: Common objects in context,

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.929092Z

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=2026-08-07T15:27:40.848369Z digest=sha256:8e77ab7a8add27f88788b7f66ff149d8b64a2220a54923e218ae0080e2b8ae71

Observation c09611ed-bad6-4b6d-b5a6-d0fedbb3776c · outbound

This paper cites Knowledge distillation with the reused teacher classifier,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Knowledge distillation with the reused teacher classifier,

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.824884Z

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=2026-08-07T15:27:40.978509Z digest=sha256:7138e4eb86e9ae2ae9238688cbbc61eed5bd6725377de6fcd8d4db6dc5f05326

Observation fb03f528-b482-4d0d-a446-a7d10a963463 · outbound

This paper cites Class attention transfer based knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Class attention transfer based knowledge distillation,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.756410Z

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=2026-08-07T15:27:41.094829Z digest=sha256:b4b080d63eb0da2b6f00219a304fd4e9cb82cd8569b0f506f35bfb9bb5d9f808

Observation 4c520fb1-b70b-4416-b9ca-e4e543f245b9 · outbound

This paper cites Multi-level logit distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Multi-level logit distillation,

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.673550Z

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=2026-08-07T15:27:41.235257Z digest=sha256:57465db9c6cb8d01f4641f20915a921e64ba8c74abef8d973894b7771ffd8c53

Observation 2cfb5423-4942-4a95-94d2-7cb2966d4faa · outbound

This paper cites Distilling knowledge via knowledge review,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Distilling knowledge via knowledge review,

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:44.027869Z

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=2026-08-07T15:27:41.348891Z digest=sha256:54963e06a46608018cce4196761e225fb303ee4e59c5d69eccbbbc7091dc1e47

Observation b06a12d0-3a00-44c5-bad6-4897748c8ba2 · outbound

This paper cites Faster r-cnn: Towards real-time object detection with region proposal networks,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Faster r-cnn: Towards real-time object detection with region proposal networks,

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.559368Z

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=2026-08-07T15:27:41.441181Z digest=sha256:b2498ea0fcc66aa9aec4aeb4b23e78b7af57317eafab71a23606387a1597a17a

Observation e559f72b-9c14-4c70-8994-fe8a9f1feda7 · outbound

This paper cites Visualizing data using t-sne.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Visualizing data using t-sne

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.423973Z

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=2026-08-07T15:27:41.607601Z digest=sha256:009603e9672cdeff5e37e082aacf87e6a7f17f1bdfbb7e5bf6020cae3e982c0a

Observation d36ba7e0-0db2-47a6-8d66-694eaae47c12 · outbound

This paper cites Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:41.661879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:41.661879Z digest=sha256:45b7e5bf17f9551ee62141756b1ee49dd5ba93a76f09407d4aa97c23635a41c5

Observation 1c1127a6-305c-42a6-b0a5-c75c7b0fa479 · outbound

This paper cites Relational knowledge distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Relational knowledge distillation,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:41.791141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:41.791141Z digest=sha256:8d5a0ad0af316c41ad2a503ce08f24e4c9d13ff2288bd7e40bd0e483b6501ae5

Observation a3818fe6-56fc-416c-b67f-1a76cca1fc33 · outbound

This paper cites Contrastive Representation Distillation.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer Contrastive Representation Distillation

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T15:27:41.869574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:27:41.869574Z digest=sha256:e404de3e0e538e3c0505fa99cd1a0226917fcbddb9c8460f34839e8879d2c564

Observation 902d1831-01c9-401f-82a4-cdd4acd83bf9 · outbound

This paper cites A comprehensive overhaul of feature distillation,.

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer A comprehensive overhaul of feature distillation,

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:27:42.274448Z

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=2026-08-07T15:27:41.962913Z digest=sha256:b9dfe68db6ba12c53ac0aaa70b1af7029fde192bd693589def0945d68fe52d49

Pith citing papers

No inbound Pith citation observations are available.