Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T05:52:28.822723Z
Paper Citation Record · LEDGER
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
As of 3 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2604.18473.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
50 of 50 outbound references displayed
- verified exact38
- verified fuzzy2
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch10
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d40296a1-7795-4449-9ab4-cc66a903c61a · outbound
This paper cites OpenCodeReasoning: Advancing Data Distillation for Competitive Coding.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T19:21:42.208861Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation da7d1394-2326-439e-9b1b-3529e3d27e0d · outbound
This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T17:30:03.293701Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 90341f8a-66e6-416a-b1cd-a35e27818c1e · outbound
This paper cites The Art of Saying No: Contextual Noncompliance in Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts The Art of Saying No: Contextual Noncompliance in Language Models
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.277383Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 963255fd-4918-4ab8-a1be-4b5e861860c7 · outbound
This paper cites AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.305553Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 7aaf3403-9515-47e1-90d0-e535e7688b59 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Training Verifiers to Solve Math Word Problems
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.295170Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 7920bb18-0da0-4be9-8b53-a9e5eb7aaf7c · outbound
This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T22:50:20.439308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation e81ba119-2e91-4adc-b8e3-7834dcc3730c · outbound
This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T11:13:05.519270Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 4d7481d8-3abc-4077-baf3-2140a4f8af75 · outbound
This paper cites Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T23:57:11.134962Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 71d2769d-2aff-4d96-96e6-da82fe28c514 · outbound
This paper cites The Llama 3 Herd of Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts The Llama 3 Herd of Models
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.307972Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ca38162c-ac9a-4f9b-8743-c484fb2ba8d3 · outbound
This paper cites OpenThoughts: Data Recipes for Reasoning Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts OpenThoughts: Data Recipes for Reasoning Models
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T04:57:51.597669Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation fae64d48-2412-475e-bd67-dae325f422c9 · outbound
This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T16:25:15.056079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 462c6ff1-6451-46e7-bc21-e7017fbe8576 · outbound
This paper cites Measuring Massive Multitask Language Understanding.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Measuring Massive Multitask Language Understanding
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T12:43:44.770948Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 897f0123-3279-4ce4-a1cb-80cf28f4ffd9 · outbound
This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Measuring Mathematical Problem Solving With the MATH Dataset
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T13:00:39.484061Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 009f6b90-0838-4ead-8c30-51dbf4f61016 · outbound
This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T21:59:02.400889Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation c311ec6a-216f-4bed-9403-ac205b2e4b33 · outbound
This paper cites TrustLLM: Trustworthiness in Large Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts TrustLLM: Trustworthiness in Large Language Models
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T11:17:09.209714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 071cf3b2-ce75-4b34-ac2a-78a2bd1fd14c · outbound
This paper cites Editing Models with Task Arithmetic.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Editing Models with Task Arithmetic
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T08:09:13.515542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation e6830057-1fd0-46ab-9ecc-6119c6aa707c · outbound
This paper cites Numinamath.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Numinamath
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T18:44:20.011126Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 44595741-3c55-4cae-9bae-497ed3b1b1ab · outbound
This paper cites Mixtral of Experts.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Mixtral of Experts
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.379043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation b2d021a9-a9e4-4494-ac69-0f3e6b60c9bf · outbound
This paper cites WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.342003Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ceef38a6-2501-4310-8074-12b52e4e37c8 · outbound
This paper cites Scaling Laws for Fine-Grained Mixture of Experts.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Scaling Laws for Fine-Grained Mixture of Experts
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.386751Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 7560be99-527d-45aa-9bef-433f1d55f931 · outbound
This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T05:06:39.239829Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation c11c9915-325d-4f10-b7cc-df47e095a4eb · outbound
This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T02:26:45.276836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 27729a76-23bc-495a-aab5-fcad434f7204 · outbound
This paper cites Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.347027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ca015b89-66bb-4a95-b1ba-42cf494c3f9a · outbound
This paper cites StarCoder: may the source be with you!.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts StarCoder: may the source be with you!
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T23:33:01.814344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 2b5c0ec3-fe0c-4ae1-9d75-7af1606d9d56 · outbound
This paper cites ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.325941Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5cb5290e-be05-415e-b994-b43b142f8936 · outbound
This paper cites Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T02:04:18.346890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation b6a92e35-e8c2-4d32-80be-b2dee0193995 · outbound
This paper cites When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T11:33:08.656299Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 9217cee9-fe65-415f-ab42-a707438df2ef · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T04:06:33.939395Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation ec3106ad-e198-4272-9961-b2226fc1fa73 · outbound
This paper cites Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.336399Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3293376e-0836-4662-86cb-871ddbc467f3 · outbound
This paper cites Olmo 3.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Olmo 3
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.323374Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 174d2a53-ae31-41a9-82b3-5dd07e1a6b26 · outbound
This paper cites 2 OLMo 2 Furious.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts 2 OLMo 2 Furious
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T16:50:29.153357Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3104be30-0604-4d01-ae26-f1705c60f6cb · outbound
This paper cites Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T18:44:20.013587Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 29f751b2-f3a1-46ca-93dc-f6758ff1ada6 · outbound
This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Reference 33
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T02:33:28.482709Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 91f0c07c-8ff5-4e20-a98d-7dee80d85be3 · outbound
This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts GPQA: A Graduate-Level Google-Proof Q&A Benchmark
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T04:00:34.729655Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 26ec9f85-bdd3-4e4a-8db5-4fdf92041243 · outbound
This paper cites Prism: Demystifying retention and interaction in mid-training.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Prism: Demystifying retention and interaction in mid-training
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.384125Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3a01b6c6-33ce-4cbc-9dbd-4b05c805d827 · outbound
This paper cites DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T00:00:28.487879Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 65263bf3-b723-43d4-9067-438df85f225a · outbound
This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Reference 37
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T08:39:28.464962Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation de7ab114-5522-4b42-b5e6-eb2e45821c64 · outbound
This paper cites FlexOlmo: Open Language Models for Flexible Data Use.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts FlexOlmo: Open Language Models for Flexible Data Use
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.391939Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5f497ec4-0856-48e6-bfc2-dbdec66ba17b · outbound
This paper cites Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Reference 39
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.344597Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1356ad6f-4a21-4a9c-bcc5-88494310d421 · outbound
This paper cites OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
Reference 40
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.366338Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 560706eb-9905-41a2-99cf-5a79bd55fb28 · outbound
This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T07:15:24.133279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 40fb062d-7989-4f89-a8cd-59dbbba29e00 · outbound
This paper cites OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
Reference 42
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.363601Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5ee285da-fd08-480d-8e6a-cbff23dd7b43 · outbound
This paper cites Measuring short-form factuality in large language models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Measuring short-form factuality in large language models
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T06:45:50.345693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 1fc28890-c1c8-498b-9bac-03023aa2e168 · outbound
This paper cites Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Reference 44
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.358483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 5c7b38cb-12c9-4564-ab41-c32015845da7 · outbound
This paper cites TIES-Merging: Resolving Interference When Merging Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts TIES-Merging: Resolving Interference When Merging Models
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.350546Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 18e838fd-0110-4524-86e1-6012c542bd7f · outbound
This paper cites Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Reference 46
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:11.355989Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 446be9ed-0905-4b7c-8f9a-3408089cfe26 · outbound
This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Reference 47
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.289994Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 3e9679a5-d046-406d-b5c2-5483a292b033 · outbound
This paper cites ACECODER: Acing Coder RL via Automated Test-Case Synthesis.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts ACECODER: Acing Coder RL via Automated Test-Case Synthesis
Reference 48
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T05:56:11.315572Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 4dac4e0d-3f34-4c37-95a9-13fc45d49019 · outbound
This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T10:03:59.570579Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Observation 0672af51-3d40-4722-873b-360ae95b024d · outbound
This paper cites Instruction-Following Evaluation for Large Language Models.
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Instruction-Following Evaluation for Large Language Models
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T05:56:11.310433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.
Pith citing papers
No inbound Pith citation observations are available.