Pith. sign in

Paper Citation Record · LEDGER

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression

As of 7 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2510.02345.

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

pith.paper-citation-record.v1
2510.02345 v4

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:50:28.595718Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 842ad0e5-cb19-4cdd-b3e7-ae15c1dc1777 · outbound

This paper cites Harder tasks need more experts: Dynamic routing in moe models.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Harder tasks need more experts: Dynamic routing in moe models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.130480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.130480Z digest=sha256:cd21c7a9a7953293cd37c3abc5d9a0dc9e6bb615d631f31e5e7eb3ae31c4b903

Observation c0d083ba-e15b-41d2-af2f-1b0ef6372b06 · outbound

This paper cites Attractive interactions in the microstructures of asymptotically flat black holes.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Attractive interactions in the microstructures of asymptotically flat black holes

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.631899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.631899Z digest=sha256:bed1615a484539ea581c7e079583eaf435e56cdc1b9c3d21a73f57f935a0e7dd

Observation 4a3a2cc9-cdb7-4f7b-9dc5-f7d63a3cf313 · outbound

This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.761856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.761856Z digest=sha256:44c32dad37c383adac005e4d1bb2d70780767dce283a9daa4ba5920b2eae5a30

Observation ef86f980-9d7c-4e0c-a8a2-de15c80d46b8 · outbound

This paper cites Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.006100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.006100Z digest=sha256:b41aa04db57c25296ad21829aa95d8f93b63fabef7ecce9710a0cf69a7bb056d

Observation e83e0882-1c5d-4f7a-9c65-94a13644f928 · outbound

This paper cites PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.127696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.127696Z digest=sha256:6a0852b25ce563127d6f37bf609e7b97de3a4882f644c0c0a8b8b05bf77028ca

Observation 0e2737ca-bfe9-4611-9c1b-b8a4addfac28 · outbound

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

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.415521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.415521Z digest=sha256:0e943e40d79caa0604dff3c9c2b09e1e0c1900f8f140981dfb0b91e904d69420

Observation ef34f6ef-dd67-4d82-9aa9-c59c0f1b628e · outbound

This paper cites HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.595718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.595718Z digest=sha256:cf2acbc7b64a84a80c834db15c3323689998472197d98af695a2f4c20524d21f

Observation 5d2835ae-e076-4e3f-bdba-cb21a34e07ed · outbound

This paper cites SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.001013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.001013Z digest=sha256:480da0d116f8ce4614afb9ede0fa91f8de1a60c836a5f257d8cd6eba70db9986

Observation edc589a1-f992-457c-a3b0-9b88ff96ed8e · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression OLMoE: Open Mixture-of-Experts Language Models

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.305370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.305370Z digest=sha256:2e23e17e2ac37e7bb4f773053b8f12566080cbaa7fa45d5b6bfcb2fad2c71fe2

Observation 21831690-3225-4fa1-9258-8824e506373c · outbound

This paper cites A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.482094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.482094Z digest=sha256:3273a4a747fb2f8f89807306a7c1e1e42b2da999d375e42f1040da57bf8e293b

Observation 1ac43f15-2835-4702-851f-0f824ce12644 · outbound

This paper cites Mixtral of Experts.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Mixtral of Experts

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.211029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.211029Z digest=sha256:dca8fd426bd7e29f32cba74d2e64bcfb903202389c817ed263e3aea0a6688e7c

Observation 97ac8fce-3ce6-4a5f-a526-1f0f6d874e6f · outbound

This paper cites Pointer Sentinel Mixture Models.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Pointer Sentinel Mixture Models

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:28.194239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:28.194239Z digest=sha256:75bbeebc632d6bf0bb159dc9250311a869ac576c1a280fe549a930d691b38b66

Observation 6c0a9910-cf7e-472d-8cbc-5efe986b71f5 · outbound

This paper cites Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.875803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.875803Z digest=sha256:46a8b161651b48c6d4f1a6c5fdd672ff5138a4e639655e7f96a2f8335fd3a1b8

Observation 3a987b89-a9f3-47b3-b2d8-29e48cb9c897 · outbound

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

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:26.925600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:26.925600Z digest=sha256:d1e750b7a1d84f89a15370228e655da809fcf09744b512249975dc485542d0c8

Observation 8cf3ad8a-9b48-4d79-aaee-355c18ad0f5c · outbound

This paper cites GLaM: Efficient Scaling of Language Models with Mixture-of-Experts.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:26.916040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:26.916040Z digest=sha256:fe851cfaa3eada236e62f844ec873d768f19fefe97cfb00f42aad13833caca88

Observation ca7fc450-2f3c-4e2f-bc11-8b76a80bf606 · outbound

This paper cites StableMoE: Stable Routing Strategy for Mixture of Experts.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression StableMoE: Stable Routing Strategy for Mixture of Experts

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:26.881379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:26.881379Z digest=sha256:97a9b59e8ea20713849e7f29cb7ceb65f4507116ce41d2f8fc8142dbd3ae30dd

Observation 4c2775ab-d0b7-4785-87a8-104764d258cc · outbound

This paper cites Mixture of Lookup Experts.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression Mixture of Lookup Experts

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.381965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.381965Z digest=sha256:fc731e35f784229d68bdb5dc45043a0caf1a7958cf4df9289eb13bb322343f53

Observation 85905def-4ea5-47ee-a46e-70d9ec76f4c0 · outbound

This paper cites MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts.

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:27.505927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:27.505927Z digest=sha256:41a54c3dad0cf175d31d3e41a4d2ea4d9a2e9556c9f94fdf9c414c393aa25e78

Pith citing papers

No inbound Pith citation observations are available.