Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients | Paper Citation Record

Observation 548c8e18-3fb0-4de8-afdf-7b65b35c6b11 · outbound

This paper cites GPT-4 Technical Report.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:05.975998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e920efe4-5f66-4ceb-9bad-6a43bad18886 · outbound

This paper cites Qwen3 Technical Report.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Qwen3 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.026466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfbf34ba-1327-4b1c-89a2-d527659dba09 · outbound

This paper cites DeepSeek-V3 Technical Report.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients DeepSeek-V3 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.096074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4fe5814-2ad8-454f-b3e3-ad912931e846 · outbound

This paper cites Large language models in medicine,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Large language models in medicine,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.150823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b636c3-05ec-4452-834c-b70f02e8ed0c · outbound

This paper cites Foundation models for generalist medical artificial intelligence,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Foundation models for generalist medical artificial intelligence,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.220507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef6c5037-6bb5-4bfd-a5a2-cb86c3df92fe · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients BloombergGPT: A Large Language Model for Finance

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.260428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba359cdb-b7b4-4cd3-8344-9274cc68f978 · outbound

This paper cites Communication-efficient learning of deep networks from decentralized data,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Communication-efficient learning of deep networks from decentralized data,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.316578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83b87fa3-101e-45f3-a54f-032387d0466a · outbound

This paper cites Federated machine learning: Concept and applications,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Federated machine learning: Concept and applications,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.375505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba43704-8e29-4fe4-8d49-21b113398a13 · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Lora: Low-rank adaptation of large language models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.407158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6a0797-7ede-4262-ae46-dbc7116bd327 · outbound

This paper cites Fedpetuning: When federated learning meets the parameter-efficient tuning methods of pre-trained language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedpetuning: When federated learning meets the parameter-efficient tuning methods of pre-trained language models,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.462462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352f90cb-4ab5-4855-a527-0d510a06ad02 · outbound

This paper cites Towards building the federatedgpt: Federated instruction tuning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Towards building the federatedgpt: Federated instruction tuning,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.547743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d809f0f-e329-414c-a786-986b37494655 · outbound

This paper cites Federated fine-tuning of large language models under heterogeneous tasks and client resources,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Federated fine-tuning of large language models under heterogeneous tasks and client resources,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.595313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6256fe-93ed-45ea-8a1f-184030457bc1 · outbound

This paper cites Heterogeneous lora for federated fine-tuning of on-device foundation models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Heterogeneous lora for federated fine-tuning of on-device foundation models,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.649430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf0f9c6-77f6-4b64-9ea9-b46a7b012600 · outbound

This paper cites Flora: Federated fine-tuning large language models with heterogeneous low- rank adaptations,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Flora: Federated fine-tuning large language models with heterogeneous low- rank adaptations,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.697223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 072d16fc-9aad-4294-b99b-709a8b2ccbf6 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.747982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b065280-6056-470a-a2e1-4fa75b08d574 · outbound

This paper cites Heterofl: Computation and communi- cation efficient federated learning for heterogeneous clients,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Heterofl: Computation and communi- cation efficient federated learning for heterogeneous clients,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.826164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600e08f4-2526-44ef-a5cd-1451aa1540d0 · outbound

This paper cites Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.884792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e85e37-50ad-439a-a707-ed26d1e5a881 · outbound

This paper cites Fedrolex: Model- heterogeneous federated learning with rolling sub-model extraction,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedrolex: Model- heterogeneous federated learning with rolling sub-model extraction,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:06.965106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b340b126-0cf2-4fcd-a36f-b4ba0da11a1c · outbound

This paper cites Depthfl : Depthwise federated learning for heterogeneous clients,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Depthfl : Depthwise federated learning for heterogeneous clients,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.016874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7151ede-a8a4-45f1-9f01-436d4c79b96a · outbound

This paper cites Scalefl: Resource-adaptive federated learning with heterogeneous clients,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Scalefl: Resource-adaptive federated learning with heterogeneous clients,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.063183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886ee4c7-030e-4e7a-9c88-808600880989 · outbound

This paper cites Communication-efficient federated learning via knowledge distillation,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Communication-efficient federated learning via knowledge distillation,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.117124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8515f5c-f8ba-4806-be32-fb4890c35116 · outbound

This paper cites Fedmkt: Federated mutual knowledge transfer for large and small language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedmkt: Federated mutual knowledge transfer for large and small language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.172525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfad150f-8eb5-485e-a9da-033e04e9881e · outbound

This paper cites PCEvolve: Private contrastive evolution for synthetic dataset generation via few- shot private data and generative APIs,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients PCEvolve: Private contrastive evolution for synthetic dataset generation via few- shot private data and generative APIs,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.238431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64fea5f8-d782-434b-b56c-2edd36e81f1d · outbound

This paper cites Explaining knowledge distillation by quantifying the knowledge,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Explaining knowledge distillation by quantifying the knowledge,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.342450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664cd6f7-3556-48d5-bbd4-49c396e45610 · outbound

This paper cites Text representation distillation via information bottleneck principle,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Text representation distillation via information bottleneck principle,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.397204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5409132f-195b-4f4d-98a0-3c63f8b670f4 · outbound

This paper cites Dual-space knowledge distillation for large language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Dual-space knowledge distillation for large language models,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.463296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479ad23d-8ed7-4133-8041-51e4f64a442f · outbound

This paper cites Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.520894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e313481-330b-4531-b863-65ab3d28da59 · outbound

This paper cites Universal cross-tokenizer distillation via approximate likelihood matching,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Universal cross-tokenizer distillation via approximate likelihood matching,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.654309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672fbd72-383e-42a2-8a3b-25562af94de3 · outbound

This paper cites Tokalign: Efficient vocabulary adaptation via token alignment,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Tokalign: Efficient vocabulary adaptation via token alignment,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.750112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad52b671-3de9-4ae1-8072-3910b9c2d8fc · outbound

This paper cites Weak-to-strong generalization: Eliciting strong capabilities with weak supervision,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Weak-to-strong generalization: Eliciting strong capabilities with weak supervision,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.871958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2b81f9-9f55-478e-8ce5-2fa1c0c5aac9 · outbound

This paper cites ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:07.981696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb82ba0-6cab-4632-8b7e-fb7546ccaa77 · outbound

This paper cites SVD-LLM: Truncation- aware singular value decomposition for large language model compres- sion,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients SVD-LLM: Truncation- aware singular value decomposition for large language model compres- sion,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.151281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49cabb85-02ef-4bcf-a5b2-6c72be864dda · outbound

This paper cites Dobi-svd: Differentiable svd for llm compression and some new perspectives,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Dobi-svd: Differentiable svd for llm compression and some new perspectives,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.223724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e654aa-ea8e-4aec-a9df-eb8d2930c14b · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Distilling the Knowledge in a Neural Network

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.279126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16e75870-6fb3-43f7-b739-a87d9b038021 · outbound

This paper cites Fedgems: Federated learning of larger server models via selective knowledge fusion,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedgems: Federated learning of larger server models via selective knowledge fusion,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.362941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e362a4-3272-4fad-aa9d-acdc9925b8d4 · outbound

This paper cites Group knowledge transfer: Federated learning of large cnns at the edge,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Group knowledge transfer: Federated learning of large cnns at the edge,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.474206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76fd635e-c057-4dc7-b457-0779acf347e3 · outbound

This paper cites Crosslm: A data- free collaborative fine-tuning framework for large and small language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Crosslm: A data- free collaborative fine-tuning framework for large and small language models,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.530540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d09c5a0-6fa2-4f27-a2a7-2fe98140f599 · outbound

This paper cites Towards diverse device heterogeneous federated learning via task arithmetic knowledge integration,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Towards diverse device heterogeneous federated learning via task arithmetic knowledge integration,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.625654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abfcdbae-9215-4567-8e59-f65ce8841430 · outbound

This paper cites Bild: Bi-directional logits difference loss for large language model distillation,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Bild: Bi-directional logits difference loss for large language model distillation,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.682517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e88e153f-dbfa-4cec-9938-46f1c5ca7b89 · outbound

This paper cites Federated dropout - A simple ap- proach for enabling federated learning on resource constrained devices,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Federated dropout - A simple ap- proach for enabling federated learning on resource constrained devices,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.762664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0f31ab-ae31-4ab6-90c7-06378d072516 · outbound

This paper cites Improving lora in privacy-preserving federated learning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Improving lora in privacy-preserving federated learning,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.834233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b14626a-de8e-451a-912d-51271cc171e1 · outbound

This paper cites FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.918611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46605947-2a43-4871-b13f-45e7194948e1 · outbound

This paper cites Federatedscope-llm: A comprehensive package for fine-tuning large language models in federated learning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Federatedscope-llm: A comprehensive package for fine-tuning large language models in federated learning,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:08.980258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c91755-9385-4992-ae97-02bf1474d3f5 · outbound

This paper cites Openfedllm: Training large language models on decentralized private data via federated learning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Openfedllm: Training large language models on decentralized private data via federated learning,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.039717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba09e67a-eed3-4a56-8cfe-05aef0a289fa · outbound

This paper cites SVD-LLM V2: optimizing singular value truncation for large language model compression,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients SVD-LLM V2: optimizing singular value truncation for large language model compression,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.156510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b096bafb-7bd5-4c2d-a484-0b1cef10954e · outbound

This paper cites Qsvd: Efficient low-rank approxi- mation for unified query-key-value weight compression in low-precision vision-language models,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Qsvd: Efficient low-rank approxi- mation for unified query-key-value weight compression in low-precision vision-language models,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.172299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf9517a-ec14-455b-8ba8-5411d472f077 · outbound

This paper cites SCAFFOLD: Stochastic controlled averaging for federated learning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients SCAFFOLD: Stochastic controlled averaging for federated learning,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.209411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc589df7-ce9b-4376-b044-3cbe41a1b2d8 · outbound

This paper cites Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.293179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896dcfcc-23c8-4de0-817b-206491cffc30 · outbound

This paper cites Loss landscapes and optimization in over-parameterized non-linear systems and neural networks,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Loss landscapes and optimization in over-parameterized non-linear systems and neural networks,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.390721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d22ddc-746a-4c5b-8899-6eba416e43bd · outbound

This paper cites On the Convergence of Local Descent Methods in Federated Learning.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients On the Convergence of Local Descent Methods in Federated Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.499421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec077df9-4bfe-4a39-9521-57da09b28a14 · outbound

This paper cites Exact and linear convergence for federated learning under arbitrary client participation is attainable,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Exact and linear convergence for federated learning under arbitrary client participation is attainable,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.649575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73b647e-cf9d-4dbf-bcd3-de2664b11b62 · outbound

This paper cites Decentralized federated averaging,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Decentralized federated averaging,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.740954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3badccf-3006-47cf-a5b0-d044e11eeb4f · outbound

This paper cites Llava- next: Improved reasoning, ocr, and world knowledge,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Llava- next: Improved reasoning, ocr, and world knowledge,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.837140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3453a1a6-421b-4fed-8a5d-8d31f03f087c · outbound

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

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:09.957426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce5968f-9bc4-40c0-99db-a5c3f3565273 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Piqa: Reasoning about physical commonsense in natural language,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.045645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9451ffa9-4fe4-4550-b1f1-715cb256c38b · outbound

This paper cites Winogrande: an adversarial winograd schema challenge at scale,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Winogrande: an adversarial winograd schema challenge at scale,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.128490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60c27b8-3ac2-487a-b76a-67d6c13bba90 · outbound

This paper cites Social iqa: Commonsense reasoning about social interactions,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Social iqa: Commonsense reasoning about social interactions,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.217301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e51e6617-9579-40fb-8c70-09f85568938f · outbound

This paper cites Hellaswag: Can a machine really finish your sentence?.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Hellaswag: Can a machine really finish your sentence?

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.334568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90efcc15-3274-44b2-a876-809d22a2bfe1 · outbound

This paper cites Choice of plausible alternatives: An evaluation of commonsense causal reasoning,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Choice of plausible alternatives: An evaluation of commonsense causal reasoning,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.424414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f068c9e1-6292-4ece-af7c-0bd5424b7734 · outbound

This paper cites Medical-flashcards,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Medical-flashcards,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.490372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbbeaef0-f790-4d39-87c8-89703c9dc90d · outbound

This paper cites Pubmedqa: A dataset for biomedical research question answering,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Pubmedqa: A dataset for biomedical research question answering,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.576823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3910e8e6-f678-4337-9a35-eca83b7e6f96 · outbound

This paper cites Medmcqa: A large- scale multi-subject multi-choice dataset for medical domain question answering,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Medmcqa: A large- scale multi-subject multi-choice dataset for medical domain question answering,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.706031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad776a3-c1bb-464a-b6ff-ac88214bf9ae · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Learn to explain: Multimodal reasoning via thought chains for science question answering,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:10.877037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a19352d-f61c-411a-bcb1-a949a0f4c322 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Vizwiz grand challenge: Answering visual questions from blind people,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.011955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae49582e-2257-47a9-800b-680173ffe48d · outbound

This paper cites Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.189086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2634f9-23f1-471a-9534-74da05849f7f · outbound

This paper cites Fedproto: Federated prototype learning across heterogeneous clients,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedproto: Federated prototype learning across heterogeneous clients,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.247638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5d367e-365e-4f9a-b0e9-398ca375bf75 · outbound

This paper cites Fedbiot: Llm local fine-tuning in federated learning without full model,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Fedbiot: Llm local fine-tuning in federated learning without full model,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.376782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94b2864-287e-47b3-a1ae-482b2879124f · outbound

This paper cites Transformer feed-forward layers are key-value memories,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Transformer feed-forward layers are key-value memories,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.518987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89cb9e97-a90c-4adb-b12a-52254e159a88 · outbound

This paper cites Locating and editing factual associations in GPT,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Locating and editing factual associations in GPT,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.586838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a41b8ae-bd26-4f9c-b1ed-40a9ac46c690 · outbound

This paper cites A unified theory of decentralized SGD with changing topology and local updates,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients A unified theory of decentralized SGD with changing topology and local updates,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.682367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dae905d6-1d69-44a7-9a01-f53624d45e09 · outbound

This paper cites Optimizing neural networks with kronecker-factored approximate curvature,.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Optimizing neural networks with kronecker-factored approximate curvature,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.755070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243b5dfd-767f-4763-ae2b-b2823ac7fe0e · outbound

This paper cites WhenAis itself square and invertible,A † coincides with the ordinary inverseA −1.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients WhenAis itself square and invertible,A † coincides with the ordinary inverseA −1

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.829720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d824d48e-4c03-4b8d-9d58-6e0c6134b7df · outbound

This paper cites an unresolved cited work.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:11.908187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1788857b-5152-430e-94a6-e0915e61d8ba · outbound

This paper cites A standard sufficient condition isf(x) =g(Ax)withgstrongly convex, whereAmay be rank-deficient [48]; compositions of this form arise naturally in overparameterized learning.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients A standard sufficient condition isf(x) =g(Ax)withgstrongly convex, whereAmay be rank-deficient [48]; compositions of this form arise naturally in overparameterized learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.031149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037e66c9-2c30-4c5d-99b5-baed6a056110 · outbound

This paper cites , λr)≻0, andS∈R r×r invertible.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients , λr)≻0, andS∈R r×r invertible

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.122939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 599e2258-6e67-406a-a055-9280a46cf78c · outbound

This paper cites By Lemma 7, fi(Σ(t+1) i )≤f i(Σ(t) i ) +⟨∇f (t) i ,Σ (t+1) i −Σ (t) i ⟩ + Leff 2 ∥Σ(t+1) i −Σ (t) i ∥2 F.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients By Lemma 7, fi(Σ(t+1) i )≤f i(Σ(t) i ) +⟨∇f (t) i ,Σ (t+1) i −Σ (t) i ⟩ + Leff 2 ∥Σ(t+1) i −Σ (t) i ∥2 F

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.247201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5600a598-c32b-44ba-961e-a6991ad7d3ed · outbound

This paper cites Using the standard iden- tity∇ z ℓCE(p,softmax(z)) = softmax(z)−p, the gradient ofL conf with respect toz s is ∇zs Lconf = (1−α)(f s −f w) +α(f s − ˆfs).

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Using the standard iden- tity∇ z ℓCE(p,softmax(z)) = softmax(z)−p, the gradient ofL conf with respect toz s is ∇zs Lconf = (1−α)(f s −f w) +α(f s − ˆfs)

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.343928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7be7efe-1673-480c-8ec7-8b9981519f35 · outbound

This paper cites Expanding Bξ =L f δrmin ( cW)yields (36).

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Expanding Bξ =L f δrmin ( cW)yields (36)

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.440117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f588a3ef-ad4f-4110-a7f0-4204c3ed882c · outbound

This paper cites an unresolved cited work.

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients Unresolved cited work

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-03T14:16:12.512676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers