Paper Citation Record · LEDGER

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

As of 16 August 2026, this Paper Citation Record lists 9 of 9 outbound references and 1 inbound Pith citation observation for arXiv:2605.27081.

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

pith.paper-citation-record.v1
2605.27081 v1

Coverage vector

measured 9 of 9 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T07:34:15.530836Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

9 of 9 outbound references displayed

verified exact2
verified fuzzy0
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 738ff0f3-2d0b-4ffd-9290-8dd68ab0648d · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference Training Verifiers to Solve Math Word Problems

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T19:03:51.008223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e2e6146d-ef46-4372-b650-dd839794794b · outbound

This paper cites FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:03:51.303845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 19eab902-1c9b-455a-87c0-d6237bd22480 · outbound

This paper cites URL https://aclanthology.org/2025.findin gs-acl.997/.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference URL https://aclanthology.org/2025.findin gs-acl.997/

Reference 3

Resolution: verified exact; doi, observed 2026-06-29T19:03:51.007116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e2622156-cdd5-4e34-a20e-46c1ed3b6d02 · outbound

This paper cites Berger, Marie Nguyen, Xun Jian, Sam H.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference Berger, Marie Nguyen, Xun Jian, Sam H

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T19:03:51.001555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 99c27e79-fc6b-4786-be29-373af5904d31 · outbound

This paper cites Empowering edge intelligence: A comprehensive survey on on-device ai models.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference Empowering edge intelligence: A comprehensive survey on on-device ai models

Reference 5

Resolution: metadata mismatch; doi, observed 2026-06-29T19:03:51.009237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7e3a6e1-2a48-41ec-b5c6-86837fd021da · outbound

This paper cites For instance, if K= 6 and C= 4 , even if Et =E t−1, the cache cannot hold all 6 experts simultaneously, so a guarantee of the form(17) no longer holds.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference For instance, if K= 6 and C= 4 , even if Et =E t−1, the cache cannot hold all 6 experts simultaneously, so a guarantee of the form(17) no longer holds

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T18:59:37.443084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc91e82-0e28-41d6-b7fd-bac9e8fb5232 · outbound

This paper cites Then even if Et−1 was fully loaded during step t−1 , some of these experts might be evicted before step t begins, and the containment in Lemma A.5 can fail.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference Then even if Et−1 was fully loaded during step t−1 , some of these experts might be evicted before step t begins, and the containment in Lemma A.5 can fail

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T18:59:37.443084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50b3d48e-c0c4-4fdd-947f-c40c68b8ef1c · outbound

This paper cites For example, with C=K , any insertion of an expert not in Et−1 forces an eviction; if the policy/prefetcher evicts from Et−1, then Et−1 ⊈C t.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference For example, with C=K , any insertion of an expert not in Et−1 forces an eviction; if the policy/prefetcher evicts from Et−1, then Et−1 ⊈C t

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T18:59:37.443084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c78c984-c4cb-480d-b3f5-f20592a8b37c · outbound

This paper cites an unresolved cited work.

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference Unresolved cited work

Reference 9

Resolution: malformed identifier; no resolver link, observed 2026-06-29T18:59:37.443084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c18475df-10cf-4ca0-86ea-1845ab5b2fba · inbound

Sticky Routing: Training MoE Models for Memory-Efficient Inference cites this paper.

Sticky Routing: Training MoE Models for Memory-Efficient Inference ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T07:34:15.530836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.