Paper Citation Record · LEDGER

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

As of 6 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 4 inbound Pith citation observations for arXiv:2412.00069.

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

pith.paper-citation-record.v1
2412.00069 v3

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-23T17:10:06.053994Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:57:24.835167Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T19:08:50.009027Z

Reference resolution

41 of 41 outbound references displayed

verified exact29
verified fuzzy2
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1bfee1b7-e09c-4e9f-8a57-5da39b558201 · outbound

This paper cites online" 'onlinestring :=.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning online" 'onlinestring :=

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T17:13:14.783007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 629ae37f-0382-4f68-86be-c5b6eca4dba7 · outbound

This paper cites write newline.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning write newline

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T17:13:14.778469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7b3971b-1360-49f3-8fd6-00c87a768ecf · outbound

This paper cites Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.033346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5775df9f-cc60-46ad-9773-c7063d682187 · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.011725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 82243946-d683-4d19-a99f-a519ac27db4c · outbound

This paper cites Language Models are Few-Shot Learners.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Language Models are Few-Shot Learners

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.006001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0a1cbc44-3106-48d0-85a1-a9eaeac23c38 · outbound

This paper cites On the Representation Collapse of Sparse Mixture of Experts.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning On the Representation Collapse of Sparse Mixture of Experts

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:13.984927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3599cab2-ef44-4b9f-b81a-d2fa199364e6 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.970101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 298e93b6-69da-4da7-aada-9b2769b04896 · outbound

This paper cites What Does BERT Look At? An Analysis of BERT's Attention.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning What Does BERT Look At? An Analysis of BERT's Attention

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.965186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2730f84b-4d4e-4cc9-9c46-f03c0a5b3e62 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.959900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 024e36e9-0a8d-4ff5-a655-948ae0d0f318 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.746102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2706ab21-131a-4f18-a019-536c991f1d89 · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.954661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0cea8f76-6e54-44e3-9152-c09242596965 · outbound

This paper cites Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.949472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c20041f7-2814-4d7a-a00f-082766b5aaab · outbound

This paper cites SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.093060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7e12475-2415-4237-acdd-b1e0d65b3126 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.087374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52bf1a05-0d58-46a7-98c3-f04bfc081d82 · outbound

This paper cites doi:10.5281/zenodo.12608602 , url =.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning doi:10.5281/zenodo.12608602 , url =

Reference 15

Resolution: verified exact; doi, observed 2026-05-23T17:13:13.052078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e460339f-0b03-4481-8c6c-db2f56d117ed · outbound

This paper cites Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.082298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2127e1e0-0b63-4d8d-b359-fa32575e8e5b · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Measuring Massive Multitask Language Understanding

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.076876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3f9f30ca-0b34-46f8-8fb8-0cea359169e7 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.773689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 409468ee-fd0e-4376-99ff-1b0b81110a8c · outbound

This paper cites Mixtral of Experts.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Mixtral of Experts

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.071380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e564d970-dbf3-4644-9b2a-799ee8102dbd · outbound

This paper cites Outlier-weighed Layerwise Sampling for LLM Fine-tuning.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Outlier-weighed Layerwise Sampling for LLM Fine-tuning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.066690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04cc05ad-d4f1-40d2-a50f-9be1250037d4 · outbound

This paper cites Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.061601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c57a42e8-79da-488c-afc3-b1fd019f1c3c · outbound

This paper cites Traditional and Heavy-Tailed Self Regularization in Neural Network Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Traditional and Heavy-Tailed Self Regularization in Neural Network Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.055892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 83e9f3d4-3413-4501-9f80-28dfd8f76307 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.770173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 959f6f8a-87b6-4515-9ec8-e0c2686d8cef · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.766720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 20b208f8-95a3-418f-88ae-3d2b4b5da2c3 · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.050878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 59bf7a80-8e88-4dfb-af07-d0f450005285 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 27

Resolution: verified exact; doi, observed 2026-05-23T17:13:13.057419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a89d51e7-941f-408c-b4ca-ff6c2c19a190 · outbound

This paper cites SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.044860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d15489b9-0f3f-4194-b92a-ea7218fe9dd1 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T17:13:14.038990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 09903d7b-c265-4199-945b-f279f7455c1f · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.017414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 599f18fb-168d-4a0c-8bb7-226cdbfa9f41 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.763462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4ade4778-53d0-4c0f-acf7-dd7093edecc5 · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.022452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6d6dec2-e449-437d-8f1c-5ac61e79c4bd · outbound

This paper cites Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:14.027533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b1deffd0-36ce-45a4-9e63-ec6f89a356e2 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning A Simple and Effective Pruning Approach for Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.979634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe6525c8-165f-49d4-baae-ee1f87057391 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.759957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f446fd88-ff78-4848-86ec-4a7d7fdf8a00 · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.756395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a005d7cd-b5b6-4c2c-bf27-c0a4b1c39292 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning LLaMA: Open and Efficient Foundation Language Models

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.974881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 64784ab2-8d62-4d22-aea7-200d7d8c17dd · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.752842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c3741258-d969-41f9-bb86-9c0da7e6646f · outbound

This paper cites an unresolved cited work.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-05-23T17:13:14.749296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe1faf90-3339-4ef4-aeea-2519e289f5dd · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:14.000037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 455d5464-fabf-4953-84e9-97f33299eacf · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning OPT: Open Pre-trained Transformer Language Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-23T17:13:13.990072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 88f66b36-7342-49c0-b134-63282d68760c · outbound

This paper cites FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models.

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:13:13.994866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 18dc9542-dbe7-4ce0-8934-929aa1388199 · inbound

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs cites this paper.

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T17:57:24.835167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0be290f-5b62-4234-98ea-3b637cc799e3 · inbound

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training cites this paper.

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-12T07:16:28.304287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d2ed94a2-b269-46d3-8b39-92b5e0a141c2 · inbound

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training cites this paper.

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:23:51.298416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9df1c44c-300f-4802-81ca-96544e1cb952 · inbound

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression cites this paper.

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-03T19:08:50.010625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.