Pith. sign in

Paper Citation Record · LEDGER

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

As of 9 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2502.04411.

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

pith.paper-citation-record.v1
2502.04411 v3

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T00:07:44.901131Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:21.281499Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T15:42:25.856629Z

Reference resolution

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy11
  • unresolved6
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 483bf4fc-fefb-4e89-93be-dbab75ed237f · outbound

This paper cites This direction discusses the layer-wise training dynamics to help shed some light on the paramter conflicts and the layer-wise adaptivity.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing This direction discusses the layer-wise training dynamics to help shed some light on the paramter conflicts and the layer-wise adaptivity

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.315838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.813777Z digest=sha256:5e7bd4dfc0890a4ff5e5b1ec6d3908dd55bb7b4c6409ab937c3fbf578b470a0b

Observation c68ab02e-1e63-4fcf-84af-ec0db929c478 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.756545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.756545Z digest=sha256:30610aeb55c5669de6a92cf00fd6c92d53585dee9db890d0345f1b1419831423

Observation 5009eaff-405f-4126-a582-dddb75a201bd · outbound

This paper cites This direction reviews some works of the OOD Detection and Generalization, shedding light on deployment of the model merging on the out-of-distribution data.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing This direction reviews some works of the OOD Detection and Generalization, shedding light on deployment of the model merging on the out-of-distribution data

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.285288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.835838Z digest=sha256:fad8879932b84e9863853e13df9e0141b43d1ceec87622ede71ed530f09684eb

Observation f20b0999-19a1-4ec7-8474-383bc9c45146 · outbound

This paper cites This direction shortly review some works about the model compression, in which many methods can be directly applied into our framework to further reduce the memory costs.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing This direction shortly review some works about the model compression, in which many methods can be directly applied into our framework to further reduce the memory costs

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.269075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.842109Z digest=sha256:3ed8826db4d6c09394df8e66c8858d825faeac159ec11cef5b1d5b081989fc7c

Observation fc5054f5-9f2e-4326-9339-8da2185b5a97 · outbound

This paper cites This direction reviews some works about how to generate new synthetic data to improve the model merging performance.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing This direction reviews some works about how to generate new synthetic data to improve the model merging performance

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.253268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.849064Z digest=sha256:3e4a08a6490a2d90e4280c51a1c2088457e5ca967cad64091c366f1686fd0754

Observation 4724ec05-0d08-4f15-84e1-b6ac32657a74 · outbound

This paper cites This direction reviews some works of the Bayesian deep learning, discussing the uncertainty and Bayesian model averaging.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing This direction reviews some works of the Bayesian deep learning, discussing the uncertainty and Bayesian model averaging

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.300506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.827619Z digest=sha256:beca3a6119eb7095cd9b4e1a1f0178a7b3d5a2698e1792ef0d49a9444c620e85

Observation db261900-342a-414c-a30b-d80cc00bd639 · outbound

This paper cites The importance measurement is based on the calibration dataset.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing The importance measurement is based on the calibration dataset

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.236265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.861094Z digest=sha256:1650eac872fd7c97424955e652822a80a7a71133b79ae1da7bc82e8dcd900323

Observation 897a805d-bc96-41dd-9267-796c0d212292 · outbound

This paper cites Because that the importance measurement is based on the calibration dataset, the computation costs is almost similar to conduct the complete forward process of the different models.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Because that the importance measurement is based on the calibration dataset, the computation costs is almost similar to conduct the complete forward process of the different models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.218277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.871244Z digest=sha256:ca1eca57bd90e8aa91b9430603b4d6ec075f8a4223452f9cc4b280a4b5a037a1

Observation d0db58af-b2ee-4cd3-9132-10c31bf29d1e · outbound

This paper cites While methods in these importance based weighted averaging methods can improve the merging performance, they still face the parameter conflicts between different models.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing While methods in these importance based weighted averaging methods can improve the merging performance, they still face the parameter conflicts between different models

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.201980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.878322Z digest=sha256:7282d6f2f158a5a2e542bf4eef756725e2671af7238acf7db1683bcc24316c66

Observation c17616e8-d1bd-4f59-8c54-99374b0869be · outbound

This paper cites Structured pruning is hardware-agnostic, facilitating accelerated inference but may degrade performance due to the removal of critical components, often necessitating fine-tuning.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Structured pruning is hardware-agnostic, facilitating accelerated inference but may degrade performance due to the removal of critical components, often necessitating fine-tuning

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.170118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.893185Z digest=sha256:cdd1612be3c99ea480646358b7b91e5b15e07734231b846234dbeb8eb83e959d

Observation 408ff6a9-4b73-4360-b7bf-bb04dfb2628b · outbound

This paper cites Orca-Math: Unlocking the potential of SLMs in Grade School Math.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Orca-Math: Unlocking the potential of SLMs in Grade School Math

Reference 1282

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.763265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.763265Z digest=sha256:ba9fc7676e54cedfee8ed230db278287159030dced25d63eccd0c8c023b9ae49

Observation cea28681-5299-4da2-a716-a8839777ab30 · outbound

This paper cites Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference

Reference 2007

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.773160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.773160Z digest=sha256:b8bca12f2d58670e23d60496c0fb750439f28155fb8e9b0ffc3147c92e230948

Observation b6117664-0a1e-4563-9f3a-43fb714b81aa · outbound

This paper cites Romeo and Juliet.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Romeo and Juliet

Reference 2016

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.152253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.901131Z digest=sha256:34f7dee66f4ee263740fda1a4f42e22cc77d01b95f93899af19d0cdc284d4dfe

Observation a2d4e280-b888-4203-9b75-300dca636753 · outbound

This paper cites You, J., Chung, J.-W., and Chowdhury, M.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing You, J., Chung, J.-W., and Chowdhury, M

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.782058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.782058Z digest=sha256:fcdc84c7dfd5789d18bf69446b7484049fe7da8e3d22167379b6dcd9bd54ae02

Observation 8011329e-b147-42bc-9335-0495b0c8aba4 · outbound

This paper cites overlapping local updates.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing overlapping local updates

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T00:08:00.185843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-09T00:07:44.885706Z digest=sha256:86e30249d08d3fe2efa879b0bbfe2adaffcd95b0eb9d9205ecab6d49f335ec5f

Observation 8a801fd8-184c-49c4-aa10-8ee180a2805d · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Explaining and Harnessing Adversarial Examples

Reference 2023

Resolution
malformed identifier
no resolver link, observed 2026-08-09T00:07:44.743046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.743046Z digest=sha256:36fed0d2cd0096a19b5e145227dd402897ad9517796fe2f46cd2d7010688e44a

Observation 24c95ae2-2e04-4bdf-904f-724de1f7ce38 · outbound

This paper cites SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.801485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.801485Z digest=sha256:1c7944db209cdf3f4dff9b868972977bba1738a679def7df71b83bcb19d5c75c

Observation 8b8f76b3-7278-4b7b-962c-88c3e9f66f7c · outbound

This paper cites Automatic Instruction Evolving for Large Language Models.

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing Automatic Instruction Evolving for Large Language Models

Reference 7261

Resolution
unresolved
no resolver link, observed 2026-08-09T00:07:44.792827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T00:07:44.792827Z digest=sha256:4ff261efa000b96d4868fc24ef72848c471f4ece8e953b28da3671ae458dd138

Pith citing papers

Observation 1c92c14e-10c5-49a3-bdaf-8a6e5ac0f3ab · inbound

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging cites this paper.

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Reference 37

Resolution
verified exact
local_arxiv, observed 2026-08-07T15:42:25.897996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T15:42:21.281499Z digest=sha256:8aa832b59fd9ae1cd1844fb1451fabb4bf87c3c1c53fc2188a7879ae901981af