Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-14T22:17:47.203589Z
Paper Citation Record · LEDGER
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
As of 18 August 2026, this Paper Citation Record lists 100 of 102 outbound references and 0 inbound Pith citation observations for arXiv:2603.27383.
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 2026-08-18T06:34:40.430872+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
100 of 102 outbound references displayed
- verified exact5
- verified fuzzy88
- unresolved6
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation f2bc25d3-01a2-4de8-a660-dc9706695a02 · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.055040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f190d60e-3608-4f0e-9b23-e7fc1b190f83 · outbound
This paper cites Prune efficiently by soft prun- ing.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Prune efficiently by soft prun- ing
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.136724Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation fca238d1-ba3d-4de2-8f97-f3a6a5745bb5 · outbound
This paper cites Deepcompress-vit: Rethinking model compression to enhance efficiency of vision transformers at the edge.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Deepcompress-vit: Rethinking model compression to enhance efficiency of vision transformers at the edge
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.942842Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8aa1a071-a43d-44d4-83f6-f888ccf1d4cd · outbound
This paper cites Piqa: Reasoning about physical commonsense in nat- ural language.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Piqa: Reasoning about physical commonsense in nat- ural language
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.141449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c4ae12fd-c781-44e5-a76d-a3859619f5f3 · outbound
This paper cites Fcp dis vit: Efficient vision transformer with neural network pruning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Fcp dis vit: Efficient vision transformer with neural network pruning
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.040035Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c0a415f4-c17d-4535-9e03-e5d836cb3168 · outbound
This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference accelera- tion for large vision-language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression An image is worth 1/2 tokens after layer 2: Plug-and-play inference accelera- tion for large vision-language models
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.979344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 694a06ce-13d2-4514-b753-c16b6d75a66e · outbound
This paper cites Adaptformer: adapting vision transformers for scalable visual recogni- tion.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Adaptformer: adapting vision transformers for scalable visual recogni- tion
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.910505Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1ef58249-1e63-42fc-a574-166ba9733a3c · outbound
This paper cites Lorashear: Efficient large language model structured pruning and knowledge recovery.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Lorashear: Efficient large language model structured pruning and knowledge recovery
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.073760Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation dce08176-ff00-4b4c-b621-fafa474762ad · outbound
This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression BoolQ: Exploring the surprising difficulty of natural yes/no questions
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.938306Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e27fd3f1-529c-40f5-baa5-45b32b35055c · outbound
This paper cites Think you have solved question answering? try arc, the ai2 reasoning challenge.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Think you have solved question answering? try arc, the ai2 reasoning challenge
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.113598Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 045ea07c-c325-479b-9ef7-28c9644caef2 · outbound
This paper cites Imagenet: A large-scale hierarchical image database.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Imagenet: A large-scale hierarchical image database
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.888124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a968fecc-59bd-4946-90a8-8d8473ef9df7 · outbound
This paper cites Comedian: Self-supervised Table 10.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Comedian: Self-supervised Table 10
Reference 12
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-14T22:18:05.127063Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9ec1fb50-bef5-435a-bc67-510021cfc5d7 · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.028168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1ec9bf6c-df39-4a63-89e1-000db8793ef1 · outbound
This paper cites Sigmoid- weighted linear units for neural network function approx- imation in reinforcement learning.Neural Networks, 107: 3–11.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Sigmoid- weighted linear units for neural network function approx- imation in reinforcement learning.Neural Networks, 107: 3–11
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.223995Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 08ecef17-8a3e-4573-b6d9-ff96379488b7 · outbound
This paper cites Hyperdiffusion: Generating implicit neu- ral fields with weight-space diffusion.2023 IEEE/CVF In- ternational Conference on Computer Vision (ICCV), pages 14254–14264.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Hyperdiffusion: Generating implicit neu- ral fields with weight-space diffusion.2023 IEEE/CVF In- ternational Conference on Computer Vision (ICCV), pages 14254–14264
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.245967Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 7aef1d85-e458-4e58-806b-413d0170699c · outbound
This paper cites Isomorphic pruning for vision models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Isomorphic pruning for vision models
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.237337Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9ce66074-28ab-4f40-b083-b3f7e8a76cbf · outbound
This paper cites The language model evaluation har- ness.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression The language model evaluation har- ness
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.205712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 109f4da0-e952-45b6-83c3-1be4b85f6e29 · outbound
This paper cites Fast r-cnn.
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.214870Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2ea0aaf7-5193-4f65-be64-e365eb8825f3 · outbound
This paper cites Pruning by block benefit: Exploring the properties of vision transformer blocks during domain adaptation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Pruning by block benefit: Exploring the properties of vision transformer blocks during domain adaptation
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.220023Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b08c0f08-772c-4d22-a59f-e6f40d6360ad · outbound
This paper cites Deep sparse rectifier neural networks.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Deep sparse rectifier neural networks
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.210295Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c2ab5e6b-d913-45f5-a92b-33e107ed5b86 · outbound
This paper cites Balf: Budgeted activation- aware low-rank factorization for fine-tuning-free model compression.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Balf: Budgeted activation- aware low-rank factorization for fine-tuning-free model compression
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.201265Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f67f741d-5a1d-4885-8c17-aace5adc09fc · outbound
This paper cites The llama 3 herd of models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression The llama 3 herd of models
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.241471Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1b8b5719-8276-4e51-bf79-269160a0414d · outbound
This paper cites Weight copy and low-rank adaptation for few-shot distillation of vision transformers.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Weight copy and low-rank adaptation for few-shot distillation of vision transformers
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.228055Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cd140a09-4bf3-44d2-8a69-48a66476f993 · outbound
This paper cites Dai, and Quoc V.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Dai, and Quoc V
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.187504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c84429ab-a114-4d92-b370-86c60c8b23f8 · outbound
This paper cites Svdiff: Compact pa- rameter space for diffusion fine-tuning.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Svdiff: Compact pa- rameter space for diffusion fine-tuning.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.183027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation af7291b4-73a5-4446-bca6-dbe1720ced32 · outbound
This paper cites Learning effi- cient vision transformers via fine-grained manifold distil- lation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Learning effi- cient vision transformers via fine-grained manifold distil- lation
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.250653Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cd6b4657-d6d9-488d-96c3-528d729e50cb · outbound
This paper cites Multi-dimensional model compression of vision transformer.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Multi-dimensional model compression of vision transformer
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.191877Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 737ffce7-078f-4cf3-818a-8e40129dd0cd · outbound
This paper cites LoRA: Low-rank adaptation of large language mod- els.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression LoRA: Low-rank adaptation of large language mod- els
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.196465Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 69f54d19-4135-432e-b8ec-de075e2e8f85 · outbound
This paper cites LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.974990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9477980c-f17c-43d8-a5f0-68f59d620463 · outbound
This paper cites HiRA: Parameter-efficient hadamard high-rank adaptation for large language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression HiRA: Parameter-efficient hadamard high-rank adaptation for large language models
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.803961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c9b88a66-92dc-4cc0-abef-009b99a65b0b · outbound
This paper cites Finding lottery tickets in vision models via data-driven spectral foresight pruning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Finding lottery tickets in vision models via data-driven spectral foresight pruning
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.132257Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a682978b-0e23-409c-87f1-a0e426e85ce8 · outbound
This paper cites Adap- tive class token knowledge distillation for efficient vi- sion transformer.Knowledge-Based Systems, 304:112531.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Adap- tive class token knowledge distillation for efficient vi- sion transformer.Knowledge-Based Systems, 304:112531
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.859504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e5728fed-01aa-4fa7-95c4-ebfb13ec8bd1 · outbound
This paper cites The need for speed: Pruning transformers with one recipe.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression The need for speed: Pruning transformers with one recipe
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.960196Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 209f5365-c068-4e52-8d5d-fa9b78abebe9 · outbound
This paper cites Krizhevsky and G.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Krizhevsky and G
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.836407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation eb5c34ae-c085-45e7-bec8-a1c279e90bfc · outbound
This paper cites Dct-vit: High-frequency pruned vision transformer with discrete cosine transform.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Dct-vit: High-frequency pruned vision transformer with discrete cosine transform
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.947139Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a15e4eed-5b5c-4688-a804-da3f66e0600d · outbound
This paper cites Discovering sparsity allocation for layer- wise pruning of large language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Discovering sparsity allocation for layer- wise pruning of large language models
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.077832Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation dbf86509-4509-4d68-a7ac-df81cd7cb434 · outbound
This paper cites Vb-lora: Extreme parameter efficient fine-tuning with vector banks.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Vb-lora: Extreme parameter efficient fine-tuning with vector banks
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.025947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 78155340-3b86-4200-aef5-d76ecda1994f · outbound
This paper cites LLaMA-VID: An image is worth 2 tokens in large language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression LLaMA-VID: An image is worth 2 tokens in large language models
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.016619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cb0e29c2-e31c-43ac-9eb0-06bb3ee86597 · outbound
This paper cites Scaling & shifting your features: A new baseline for efficient model tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Scaling & shifting your features: A new baseline for efficient model tuning
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.154887Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation fb591250-45f6-42c8-992f-f67c05bef274 · outbound
This paper cites Inflora: Interference-free low-rank adaptation for continual learning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Inflora: Interference-free low-rank adaptation for continual learning
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.069058Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 46bec15a-e612-431d-a25e-046e3af86522 · outbound
This paper cites 3-in-1: 2d rotary adapta- tion for efficient finetuning, efficient batching and compos- ability.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression 3-in-1: 2d rotary adapta- tion for efficient finetuning, efficient batching and compos- ability
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.009842Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8314b43e-193a-4184-b74a-c2cf6dd41610 · outbound
This paper cites Slimgpt: Layer-wise structured pruning for large language models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Slimgpt: Layer-wise structured pruning for large language models
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.794762Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4053e72c-7995-423d-a698-a2b05d22ef8f · outbound
This paper cites SVFT: Parameter-efficient fine-tuning with singular vectors.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression SVFT: Parameter-efficient fine-tuning with singular vectors
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.831871Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2ecb8b00-0049-4748-8c5a-05521c3e1f16 · outbound
This paper cites Pruning via merging: Com- pressing LLMs via manifold alignment based layer merg- ing.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Pruning via merging: Com- pressing LLMs via manifold alignment based layer merg- ing
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.087364Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a7d838b8-7ca2-4a04-b747-a55ddda86988 · outbound
This paper cites Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.082659Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4578e04c-df38-4407-b995-c4dd6450d2b1 · outbound
This paper cites Small scale data-free knowledge distillation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Small scale data-free knowledge distillation
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.099622Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 7a43ddb2-7670-41ee-84fa-34fc6f306dc5 · outbound
This paper cites Dora: weight-decomposed low-rank adaptation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Dora: weight-decomposed low-rank adaptation
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.808805Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 961bbaf0-ec23-45dc-9ae9-9a80bf1d8e29 · outbound
This paper cites Black, Adrian Weller, and Bernhard Sch ¨olkopf.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Black, Adrian Weller, and Bernhard Sch ¨olkopf
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.991992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation af36c8cc-4fe4-491a-802b-7672cb0243d7 · outbound
This paper cites Decoupled weight de- cay regularization.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Decoupled weight de- cay regularization
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.933859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 3ce3e647-972c-4caf-9ac8-8c170ce63a26 · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 50
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:04.854727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 40a00d95-5495-4d0a-a373-44afca1c5838 · outbound
This paper cites Prune and merge: Efficient token compression for vision transformer with spatial in- formation preserved.IEEE Transactions on Multimedia, 27:4670–4683.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Prune and merge: Efficient token compression for vision transformer with spatial in- formation preserved.IEEE Transactions on Multimedia, 27:4670–4683
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.178160Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b98c801d-73ad-4c73-a0fe-a2cfe2ab992d · outbound
This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Can a suit of armor conduct electricity? a new dataset for open book question answering
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.924330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9191b26b-dd0c-46c8-927f-4e22ccaeee0c · outbound
This paper cites RoSA: Accurate parameter-efficient fine-tuning via robust adaptation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression RoSA: Accurate parameter-efficient fine-tuning via robust adaptation
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.905533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 73c1fa0a-49da-4d73-818f-73ae7f44ba6c · outbound
This paper cites RoSA: Accurate parameter-efficient fine-tuning via robust adaptation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression RoSA: Accurate parameter-efficient fine-tuning via robust adaptation
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.928088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a5ea0b6b-2784-4edd-a99c-36d45f401cec · outbound
This paper cites Automated flower classification over a large number of classes.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Automated flower classification over a large number of classes
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.021512Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2f34a2f6-39c0-47bf-98e7-f6c03154abbc · outbound
This paper cites Fair-vpt: Fair visual prompt tuning for image classification.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Fair-vpt: Fair visual prompt tuning for image classification
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.874748Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 7ec1d2a2-cfa1-4d9f-96bf-1027a2a35df6 · outbound
This paper cites Data-free Weight Compress and Denoise for Large Language Models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Data-free Weight Compress and Denoise for Large Language Models
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:03.999999Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b50dce33-ff2d-4524-83ec-a8016949c9bf · outbound
This paper cites Plummer, Nikoli Dryden, Julius Frost, Torsten Hoefler, and Kate Saenko.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Plummer, Nikoli Dryden, Julius Frost, Torsten Hoefler, and Kate Saenko
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.850558Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 22b8286a-bce4-4fde-a96f-2df8ca337ee2 · outbound
This paper cites Recognizing in- door scenes.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Recognizing in- door scenes
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.232754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 89790b05-372d-4626-bea6-ed32b9804af9 · outbound
This paper cites Venkatesh Babu.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Venkatesh Babu
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.840991Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a61fd0e5-3ccf-4f7b-901e-8e569e8ca8eb · outbound
This paper cites MELoRA: Mini-ensemble low-rank adapters for parameter-efficient fine-tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression MELoRA: Mini-ensemble low-rank adapters for parameter-efficient fine-tuning
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.996245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e70e5054-4513-47d7-a255-320687bdebde · outbound
This paper cites Winogrande: an adversarial winograd schema challenge at scale.Commun.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Winogrande: an adversarial winograd schema challenge at scale.Commun
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.004782Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f92ea45a-e7e4-448e-80d4-f6eaee0220ab · outbound
This paper cites Social IQa: Commonsense rea- soning about social interactions.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Social IQa: Commonsense rea- soning about social interactions
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.150292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 3511ae88-7de0-42cb-92d6-4f30194bb6e3 · outbound
This paper cites Learning implicitly re- current CNNs through parameter sharing.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Learning implicitly re- current CNNs through parameter sharing
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.900654Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b3a04812-57df-4dd4-aea2-da69ced4f808 · outbound
This paper cites You only prune once: Designing calibration- free model compression with policy learning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression You only prune once: Designing calibration- free model compression with policy learning
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.108993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 446a5487-f2f6-423b-aac0-f694ef964664 · outbound
This paper cites Pro- vpt: Distribution-adaptive visual prompt tuning via prompt relocation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Pro- vpt: Distribution-adaptive visual prompt tuning via prompt relocation
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.063820Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cb49eef2-ff18-401d-a49c-9f8578789311 · outbound
This paper cites Learning Compact Vision Tokens for Efficient Large Multimodal Models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Learning Compact Vision Tokens for Efficient Large Multimodal Models
Reference 67
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.014300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bb6f703d-4cee-4d26-a111-1429808c8d65 · outbound
This paper cites UPop: Unified and progressive pruning for compressing vision-language transformers.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression UPop: Unified and progressive pruning for compressing vision-language transformers
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.894713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0035b8d8-4299-4d27-96cf-edc77f80ecf1 · outbound
This paper cites See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition
Reference 69
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.008009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5d9e6d6e-3842-481e-924c-f2f1181e22fb · outbound
This paper cites Sparse low rank factorization for deep neural network compression.Neurocomputing, 398:185– 196.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Sparse low rank factorization for deep neural network compression.Neurocomputing, 398:185– 196
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.031289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b38ca952-3652-4215-b574-e7f5c70b7b09 · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 71
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.163692Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 98290452-eb88-45b7-9dfb-990814f67b7a · outbound
This paper cites Tukan, A.
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.049394Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a7b0e86a-0645-413e-9368-9d96e07c5d6a · outbound
This paper cites DyLoRA: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression DyLoRA: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.104407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation be8793e0-c720-4803-888f-0211a135442d · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 74
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:04.822698Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8ae7d75a-82a3-40b5-b7a1-046ac6ce8365 · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 75
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:04.818267Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d70558d8-57a0-4518-8235-f774182d82cb · outbound
This paper cites an unresolved cited work.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Unresolved cited work
Reference 76
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:04.863791Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1775e6a1-9f4f-43fa-b4e6-77ea663404d1 · outbound
This paper cites Basis sharing: Cross-layer parameter sharing for large language model compression.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Basis sharing: Cross-layer parameter sharing for large language model compression
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.987623Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 65fe1fcf-6e3c-4719-870b-4fe3be8e676d · outbound
This paper cites Neural network pa- rameter diffusion.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Neural network pa- rameter diffusion
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.915213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4614fa46-7ad9-4730-86ed-cf66b1b7bdfd · outbound
This paper cites SVD- LLM: Truncation-aware singular value decomposition for large language model compression.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression SVD- LLM: Truncation-aware singular value decomposition for large language model compression
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.118291Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 94192cfc-b58c-4ae5-9e3c-0e3f7cbf0654 · outbound
This paper cites Revisiting the power of prompt for visual tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Revisiting the power of prompt for visual tuning
Reference 80
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.813704Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5e6a7a86-bb03-4200-8bf9-c061810860f4 · outbound
This paper cites Kd- detr: Knowledge distillation for detection transformer with consistent distillation points sampling.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Kd- detr: Knowledge distillation for detection transformer with consistent distillation points sampling
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.969563Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c11f5501-f739-4fb1-97e0-cbe300c04817 · outbound
This paper cites Learning to prompt for contin- ual learning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Learning to prompt for contin- ual learning
Reference 82
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.059209Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b7ef24d6-acce-4bc9-b04a-ec6f7248178f · outbound
This paper cites Integer quantization for deep learn- ing inference: Principles and empirical evaluation.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Integer quantization for deep learn- ing inference: Principles and empirical evaluation
Reference 83
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.799436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c02927bd-5965-4622-97a9-fa2c29b458a1 · outbound
This paper cites Efficient Distortion-Minimized Layerwise Pruning .IEEE Transac- tions on Pattern Analysis & Machine Intelligence, 47(10): 9298–9315.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Efficient Distortion-Minimized Layerwise Pruning .IEEE Transac- tions on Pattern Analysis & Machine Intelligence, 47(10): 9298–9315
Reference 84
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.845868Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6667272c-fa21-4f37-8018-da4b5fcb18c8 · outbound
This paper cites LaCo: Large lan- guage model pruning via layer collapse.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression LaCo: Large lan- guage model pruning via layer collapse
Reference 85
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.956280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 612ed8f7-a756-4acd-a8d9-49def21b0bff · outbound
This paper cites Vitkd: Feature-based knowledge distil- lation for vision transformers.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Vitkd: Feature-based knowledge distil- lation for vision transformers
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.000557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation df90ee04-6cd9-4fb3-83bd-b921dba7fa2a · outbound
This paper cites DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
Reference 87
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.021759Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f1da86e8-c6c2-4239-890d-c19227f95d91 · outbound
This paper cites Once for both: Single stage of importance and sparsity search for vision transformer compression.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Once for both: Single stage of importance and sparsity search for vision transformer compression
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.869189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ef910760-45ef-4dfa-8c56-a6aebffeeef4 · outbound
This paper cites Yu, Jianlong Chang, Haixin Wang, Lingbo Liu, Shijie Wang, Zhiyu Wang, Junfan Lin, Lingxi Xie, Haojie Li, Zhouchen Lin, Qi Tian, and Chang Wen Chen.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Yu, Jianlong Chang, Haixin Wang, Lingbo Liu, Shijie Wang, Zhiyu Wang, Junfan Lin, Lingxi Xie, Haojie Li, Zhouchen Lin, Qi Tian, and Chang Wen Chen
Reference 89
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.920207Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d636d0c7-1315-4aa7-88ae-039673e45d14 · outbound
This paper cites Yu and J.
Reference 90
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.827210Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6ae55e2b-179b-4862-bba8-0408ef42e0f3 · outbound
This paper cites Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th Annual Meet- ing of the Association for Computational Linguistics, pages 4791–4800.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th Annual Meet- ing of the Association for Computational Linguistics, pages 4791–4800
Reference 91
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.964587Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 48b0fdf7-7bc3-4c6d-ae1c-cd0d6164b7f2 · outbound
This paper cites Vi- sual fourier prompt tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Vi- sual fourier prompt tuning
Reference 92
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.983717Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 7fdaf10f-a96e-4726-a54a-090941389422 · outbound
This paper cites A large-scale study of represen- tation learning with the visual task adaptation benchmark.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression A large-scale study of represen- tation learning with the visual task adaptation benchmark
Reference 93
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.036040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a9b2a52b-5b55-4e9f-9b24-d380ec27aac6 · outbound
This paper cites Metadiff: Meta- learning with conditional diffusion for few-shot learning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Metadiff: Meta- learning with conditional diffusion for few-shot learning
Reference 94
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.173522Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 028b333c-aa4a-485d-a548-ee9c844d3126 · outbound
This paper cites Dense vision transformer compression with few samples.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Dense vision transformer compression with few samples
Reference 95
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.092823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8c8dde77-e163-42b4-ba8d-cbd4fbceb34e · outbound
This paper cites Minivit: Compressing vi- sion transformers with weight multiplexing.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Minivit: Compressing vi- sion transformers with weight multiplexing
Reference 96
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.145770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0c96fb7f-5b91-4c97-bae8-86f48ab8719f · outbound
This paper cites Zhang, X.
Reference 97
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.951504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 1dbdf622-ff0c-4db6-b04d-d3960cbf8a69 · outbound
This paper cites LoRAPrune: Structured pruning meets low-rank parameter-efficient fine- tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression LoRAPrune: Structured pruning meets low-rank parameter-efficient fine- tuning
Reference 98
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:04.883173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4d871a7f-f28b-488e-b65c-bde5f12174cb · outbound
This paper cites Intra-head pruning for vision transformers via inter-layer dimension relationship modeling.Neural Networks, 190: 107656.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Intra-head pruning for vision transformers via inter-layer dimension relationship modeling.Neural Networks, 190: 107656
Reference 99
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.122568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 37294b73-4ffb-4407-ae35-e63a2f6fd513 · outbound
This paper cites Adaptive budget allocation for parameter-efficient fine- tuning.
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Adaptive budget allocation for parameter-efficient fine- tuning
Reference 100
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T22:18:05.159342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Pith citing papers
No inbound Pith citation observations are available.