Paper Citation Record · LEDGER

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

As of 15 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 8 inbound Pith citation observations for arXiv:2505.15875.

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

pith.paper-citation-record.v1
2505.15875 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:18:17.363482Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:12:37.078175Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T21:36:34.253420Z

Reference resolution

53 of 53 outbound references displayed

verified exact2
verified fuzzy7
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 374dd8eb-7c1f-45f3-b45c-4fb15dbf9a8f · outbound

This paper cites Qwen Technical Report.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Qwen Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:12.986750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb2e1199-6efc-4846-bf2a-042b7de54e16 · outbound

This paper cites IterIS: Iterative Inference-Solving Alignment for LoRA Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging IterIS: Iterative Inference-Solving Alignment for LoRA Merging

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.023940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a694091f-339f-4428-b814-cf994ce96223 · outbound

This paper cites Are we on the right way for evaluating large vision- language models? InThe Thirty-eighth Annual Conference on Neural Information Processing Systems.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Are we on the right way for evaluating large vision- language models? InThe Thirty-eighth Annual Conference on Neural Information Processing Systems

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:19.826819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3be474fe-0891-48df-b951-a51a068ff86e · outbound

This paper cites Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.165282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14f1c9b-c908-4066-8b7e-88934f5c2f31 · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging BERT: Pre-training of deep bidirectional transformers for language understanding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.247695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1072229-6ad9-4c34-aafa-bbe7b6a745ec · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging An image is worth 16x16 words: Transformers for image recognition at scale

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.320677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb08520-0f4e-40fd-a817-9cfd76b0a1f2 · outbound

This paper cites LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.372715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fb3381-3969-46e4-8b98-fc1214a75621 · outbound

This paper cites Parameter Competition Balancing for Model Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Parameter Competition Balancing for Model Merging

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.424264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbde679-0191-4f4c-8b00-ea23ca1e9e7c · outbound

This paper cites Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.485270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b4bca0-b618-4b8d-8454-b6773da80905 · outbound

This paper cites Task Singular Vectors: Reducing Task Interference in Model Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Task Singular Vectors: Reducing Task Interference in Model Merging

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.587516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673ea1df-db05-42c6-8d40-837941c8c87a · outbound

This paper cites The Llama 3 Herd of Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.685920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0500b654-d915-40e8-80f4-7054580dc7b0 · outbound

This paper cites Measuring massive multitask language understanding.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Measuring massive multitask language understanding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.783257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d86f0857-4418-478f-9300-27eed69e836f · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:13.882003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3632423-334d-47db-a5b7-d43468666cfa · outbound

This paper cites DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:18:18.171673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9809e0f4-c4b5-432e-bdf4-d052e4d9b642 · outbound

This paper cites Lorahub: Efficient cross-task generalization via dynamic lora composition.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Lorahub: Efficient cross-task generalization via dynamic lora composition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:19.642169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dc924dde-bae9-46db-b75d-1a34ae681fd4 · outbound

This paper cites EMR-Merging: Tuning-Free High-Performance Model Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging EMR-Merging: Tuning-Free High-Performance Model Merging

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.111064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d4eea1-52da-46bf-ae82-a1e422264d01 · outbound

This paper cites Editing Models with Task Arithmetic.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Editing Models with Task Arithmetic

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.191349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b881df-46f5-4268-aecd-7d40a0bf8aae · outbound

This paper cites Dataless Knowledge Fusion by Merging Weights of Language Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Dataless Knowledge Fusion by Merging Weights of Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.269333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76c4e9b0-951b-446b-b876-7515769d7f85 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Evaluating object hallucination in large vision-language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.318592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57a93963-4e07-4d4d-b47c-307f56ec662b · outbound

This paper cites Truthfulqa: Measuring how models mimic human falsehoods.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Truthfulqa: Measuring how models mimic human falsehoods

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.371628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a50f63-440a-4847-a416-b38c6d0fbe03 · outbound

This paper cites Dora: Weight-decomposed low-rank adaptation.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Dora: Weight-decomposed low-rank adaptation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.441931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b2143ad-9bd2-4ecb-a8fe-e40c8aa7a58b · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.514408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6571b98-3daf-4790-8ead-3083cd281e19 · outbound

This paper cites Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.619323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554783ab-00ef-4d82-8bb5-9115eeb4112d · outbound

This paper cites Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.720177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7a7f02-fbe5-4f4a-b294-0e6c5ba8505d · outbound

This paper cites Merging models with fisher-weighted averaging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Merging models with fisher-weighted averaging

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.784619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d38df3d-4aa8-4730-a565-a6bd9436d48c · outbound

This paper cites K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:14.885352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6abb90ea-8694-41f9-beb6-923b39a4a2f9 · outbound

This paper cites Bbq: A hand-built bias benchmark for question answering.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Bbq: A hand-built bias benchmark for question answering

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:19.376822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7df86300-7fa2-47fe-b0c1-1961959d0470 · outbound

This paper cites Lora soups: Merging loras for practical skill composition tasks.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Lora soups: Merging loras for practical skill composition tasks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:19.197140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4b89969d-936b-4c77-937a-651b5a03df50 · outbound

This paper cites Less is More: Efficient Model Merging with Binary Task Switch.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Less is More: Efficient Model Merging with Binary Task Switch

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.177560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454bdf0e-5ab6-4de2-bffb-eac1615f2ccc · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.239875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7434243c-4eea-4545-9f17-5484351e70b3 · outbound

This paper cites LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.313964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6534a1a8-8bec-439f-9798-584284540b02 · outbound

This paper cites Model merging with svd to tie the knots.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Model merging with svd to tie the knots

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:18.993413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b7185bbc-fe83-418a-b70d-40060d49cd21 · outbound

This paper cites Fusionbench: A compre- hensive benchmark of deep model fusion.arXiv preprint arXiv:2406.03280, 2024.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Fusionbench: A compre- hensive benchmark of deep model fusion.arXiv preprint arXiv:2406.03280, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.473384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c0a394-d8c0-42f0-809d-a3deb7706801 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging LLaMA: Open and Efficient Foundation Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.544192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1bc9c3-67d4-4ed3-a908-2d39b3054b60 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.648714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52de173e-7036-416f-9c29-17ec5764c0e5 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.725870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d08b7e25-4b38-435a-bd00-2853edf856e3 · outbound

This paper cites Mixture of lora experts.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Mixture of lora experts

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:15.829600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59cca800-c57d-48a4-928f-f0f41102334a · outbound

This paper cites Grok 3: The most powerful AI in the world is here, February 2025.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Grok 3: The most powerful AI in the world is here, February 2025

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:18.755021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 77dde7e8-deb1-4bc6-88a9-c84577022529 · outbound

This paper cites Multi-Task Model Merging via Adaptive Weight Disentanglement.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Multi-Task Model Merging via Adaptive Weight Disentanglement

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.048377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0efb7827-0533-4e6f-88c4-d49a50d9d701 · outbound

This paper cites Ties-merging: Resolving interference when merging models.Advances in Neural Information Processing Systems, 36, 2024.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Ties-merging: Resolving interference when merging models.Advances in Neural Information Processing Systems, 36, 2024

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.144876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3666d29a-6d0a-41a0-af16-58b4394d93d0 · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.254802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d628249-9cd9-4000-9aef-f59d156f5454 · outbound

This paper cites Adamerging: Adaptive model merging for multi-task learning.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Adamerging: Adaptive model merging for multi-task learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.335718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ec53533-33fc-42e7-a2e1-a101b6b37c4b · outbound

This paper cites LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.447627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193c8f26-43a8-4230-acd9-da756a51a7f7 · outbound

This paper cites Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.528692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c8d5f32-97cb-4190-80b0-b0c7d0119a6b · outbound

This paper cites Language models are super mario: Absorbing abilities from homologous models as a free lunch.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Language models are super mario: Absorbing abilities from homologous models as a free lunch

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.644774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 643366b9-a882-4792-b2ff-70fd6e96e2f5 · outbound

This paper cites Parameter efficient merging for multimodal large language models with complementary parameter adaptation.arXiv preprint arXiv:2502.17159, 2025.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Parameter efficient merging for multimodal large language models with complementary parameter adaptation.arXiv preprint arXiv:2502.17159, 2025

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.757018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2c62e9-ea2b-4a07-9964-07c4af6fbcae · outbound

This paper cites LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.833605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1035df42-a5ac-4642-a5a7-420b7312c0d9 · outbound

This paper cites Nature-Inspired Population-Based Evolution of Large Language Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Nature-Inspired Population-Based Evolution of Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:16.940786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3731de2-37b8-4fa6-b694-937eca1c07d0 · outbound

This paper cites DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:17.035650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e04184c-d4dc-46e1-b18e-25b15187631a · outbound

This paper cites Model-glue: Democratized llm scaling for a large model zoo in the wild.Advances in Neural Information Processing Systems, 37:13349–13371, 2024.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Model-glue: Democratized llm scaling for a large model zoo in the wild.Advances in Neural Information Processing Systems, 37:13349–13371, 2024

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:18:18.462577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 938d036e-6a7c-45d9-88ab-fb1fe6b23d4d · outbound

This paper cites Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:17.165527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 223daaed-73e4-4506-8e68-3e28830c3994 · outbound

This paper cites FREE-Merging: Fourier Transform for Efficient Model Merging.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging FREE-Merging: Fourier Transform for Efficient Model Merging

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T15:18:17.248316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f31194d-1653-4156-bc4b-884ef6c7bbcc · outbound

This paper cites HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models.

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:18:17.582621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation 40c5e453-f89c-4a70-8ff9-57580ddbeb7c · inbound

The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants cites this paper.

The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:37.078175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66cc3980-e59f-4188-bb7b-6bf77bb65892 · inbound

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer cites this paper.

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:36:06.912228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ebd81ed2-953c-4d3f-a48e-4ef165b0424e · inbound

M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models cites this paper.

M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:01:22.646157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3fdfccb0-cf02-40d9-b1a9-69873c2ba457 · inbound

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation cites this paper.

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-21T11:24:08.732928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b35bd354-040c-4dc8-afcb-e4b4f3edd7ea · inbound

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter cites this paper.

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T01:56:27.702011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7c58f5d1-ab76-4194-9e14-5384a553eabc · inbound

Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting cites this paper.

Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 67

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:36:27.297628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 868668de-422f-4284-b183-1411e2ed44c8 · inbound

Online Data Selection Is Implicit Alignment cites this paper.

Online Data Selection Is Implicit Alignment Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T21:36:34.254828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 636950ec-ce25-42a7-ad6c-003386c1cd34 · inbound

MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration cites this paper.

MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T07:52:08.823198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.