Paper Citation Record · LEDGER

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators

As of 13 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.17371.

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

pith.paper-citation-record.v1
2607.17371 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:15:09.084823Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact1
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7a6fd6a8-8ae0-44f3-a810-2f9786bdb8e0 · outbound

This paper cites A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:03.535634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d6e03a-6c14-437e-9038-e87a33029977 · outbound

This paper cites Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:03.628144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 177f2b18-9667-43cf-adf7-7f19de3091ba · outbound

This paper cites Are vision transformers more data hungry than newborn visual systems?,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Are vision transformers more data hungry than newborn visual systems?,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:03.742579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d272821d-555a-45e4-96fe-9a70d61d5799 · outbound

This paper cites Edge Intelligence: Empowering Intelligence to the Edge of Network,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Edge Intelligence: Empowering Intelligence to the Edge of Network,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:03.865451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce49a4f-fff6-4301-b4df-aa130220d4de · outbound

This paper cites Parameter-efficient fine-tuning of large-scale pre-trained language models,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Parameter-efficient fine-tuning of large-scale pre-trained language models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:03.988409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523706dc-219a-4541-afca-0bf69c9882e1 · outbound

This paper cites Survey: federated learning data security and privacy-preserving in edge-Internet of Things,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Survey: federated learning data security and privacy-preserving in edge-Internet of Things,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.113587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07d6ef90-a12e-412e-823a-c9f4993b1aab · outbound

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

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Communication-efficient learning of deep networks from decentralized data,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.271600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3057731-2719-4c2b-a8eb-ebe66214c4b0 · outbound

This paper cites A Comprehensive Survey of Continual Learning: Theory, Method and Application,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators A Comprehensive Survey of Continual Learning: Theory, Method and Application,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.396867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda7ccbd-d6f3-44ba-9be9-54043dd54f38 · outbound

This paper cites PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy -Efficient ReRAM,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy -Efficient ReRAM,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.503905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a073ddf-fe86-4a53-ad81-fb640e32b39a · outbound

This paper cites Compute -in-Memory Chips for Deep Learning: Recent Trends and Prospects,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Compute -in-Memory Chips for Deep Learning: Recent Trends and Prospects,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.586550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec27c97-60e2-4c03-bc9e-bae4912efd16 · outbound

This paper cites Architectures and Circuits for Analog -memory-based Hardware Accelerators for Deep Neural Networks (Invited),.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Architectures and Circuits for Analog -memory-based Hardware Accelerators for Deep Neural Networks (Invited),

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.645268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2751ab52-92c0-434f-9f2d-4877d756a2d9 · outbound

This paper cites MobileNetV2: Inverted Residuals and Linear Bottlenecks,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators MobileNetV2: Inverted Residuals and Linear Bottlenecks,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.651421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 069d05f7-8794-46a1-9b62-1fa16837bfc7 · outbound

This paper cites DNN+NeuroSim V2.0: An End -to-End Benchmarking Framework for Compute -in-Memory Accelerators for On -Chip Training,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators DNN+NeuroSim V2.0: An End -to-End Benchmarking Framework for Compute -in-Memory Accelerators for On -Chip Training,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.737523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f7d714-6f90-4d8e-ba2e-9515b78a9bfe · outbound

This paper cites Efficient On -Device Training via Gradient Filtering,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Efficient On -Device Training via Gradient Filtering,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:04.839853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5449bf73-7d18-45cd-8907-3fdd799bdf0f · outbound

This paper cites Universal language model fine -tuning for text classification,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Universal language model fine -tuning for text classification,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.006899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a22d36e5-eee2-4e63-af2a-2eb8d0e8c3ba · outbound

This paper cites Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-01T18:18:48.310863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 02203f92-021e-44b9-aa2d-4e9c2b2ebb25 · outbound

This paper cites What is being transferred in transfer learning?,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators What is being transferred in transfer learning?,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.257996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ed8c521-a6fc-4130-b4b8-621712c3b89c · outbound

This paper cites Deep Residual Learning for Image Recognition,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Deep Residual Learning for Image Recognition,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.373239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9769f94b-e7c4-45fc-b232-836173e99140 · outbound

This paper cites In -Memory Computing in Emerging Memory Technologies for Machine Learning: An Overview,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators In -Memory Computing in Emerging Memory Technologies for Machine Learning: An Overview,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.488446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85468797-e4d5-4e22-9aaf-a2f997c85700 · outbound

This paper cites ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.655648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c69ff88c-0042-4c67-bb97-c64e95d26dc2 · outbound

This paper cites HuNT: Exploiting Heterogeneous PIM Devices to Design a 3 -D Manycore Architecture for DNN Training,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators HuNT: Exploiting Heterogeneous PIM Devices to Design a 3 -D Manycore Architecture for DNN Training,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.773303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 098172f6-9301-4e3d-88e9-d13ca12d8cf5 · outbound

This paper cites Hybrid RRAM/SRAM in -Memory Computing for Robust DNN Acceleration,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Hybrid RRAM/SRAM in -Memory Computing for Robust DNN Acceleration,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:05.923306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a9b96b1-3a35-4762-8453-36560de0ab02 · outbound

This paper cites Surgical fine -tuning improves adaptation to distribution shifts,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Surgical fine -tuning improves adaptation to distribution shifts,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.069741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 591288dc-2435-4750-8cf5-65b8c3a352ac · outbound

This paper cites Deep residual learning for image recognition: A survey,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Deep residual learning for image recognition: A survey,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.228445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc3e5799-9f2a-49d8-8c66-9bd5be9646a7 · outbound

This paper cites SpotTune: Transfer Learning Through Adaptive Fine - Tuning,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators SpotTune: Transfer Learning Through Adaptive Fine - Tuning,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.354492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e40497ef-670d-49c6-aa4b-9f7841134afa · outbound

This paper cites Automatic layer selection for transfer learning and quantitative evaluation of layer effectiveness,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Automatic layer selection for transfer learning and quantitative evaluation of layer effectiveness,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.541125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f57257-9060-413e-a6ad-4b5d28fff8cf · outbound

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

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Lora: Low-rank adaptation of large language models.,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.712495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6c632c-1a86-4617-8061-a023105339a7 · outbound

This paper cites Few -shot parameter -efficient fine -tuning is better and cheaper than in-context learning,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Few -shot parameter -efficient fine -tuning is better and cheaper than in-context learning,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.848730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11dd851-79fa-47eb-a3b3-2995b780cf29 · outbound

This paper cites Language models are few -shot learners,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Language models are few -shot learners,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:06.938401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886874e9-ef49-4fa1-b1be-e168bbd264cd · outbound

This paper cites Lora-c: Parameter-efficient fine-tuning of robust cnn for iot devices,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Lora-c: Parameter-efficient fine-tuning of robust cnn for iot devices,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.017478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa222c81-8ecf-4583-886d-e4b2e0aa23d8 · outbound

This paper cites PipeLayer: A Pipelined ReRAM -Based Accelerator for Deep Learning,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators PipeLayer: A Pipelined ReRAM -Based Accelerator for Deep Learning,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.095306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97cdc2d-22d3-463b-b3a1-d4ee466928ed · outbound

This paper cites FARe: Fault-Aware GNN Training on ReRAM-Based PIM Accelerators,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators FARe: Fault-Aware GNN Training on ReRAM-Based PIM Accelerators,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.247299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3062cbd9-61c5-40ea-9e08-638ba1defc7e · outbound

This paper cites Improving neural networks by preventing co - adaptation of feature detectors,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Improving neural networks by preventing co - adaptation of feature detectors,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.414703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33137e6e-aee9-4e9c-b913-8c2e0c444a45 · outbound

This paper cites Deep networks with stochastic depth,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Deep networks with stochastic depth,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.504019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07bb7b0c-7c43-4a76-94fb-0dca145f694b · outbound

This paper cites DyLoRA: Parameter-efficient tuning of pre -trained models using dynamic search-free low-rank adaptation,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators DyLoRA: Parameter-efficient tuning of pre -trained models using dynamic search-free low-rank adaptation,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.691633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6baaca-bb5d-4849-847c-3925f82d4d79 · outbound

This paper cites Learning ordered representations with nested dropout,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Learning ordered representations with nested dropout,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.867912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc69649-008e-40c6-95fc-9c6a4e3eb0bf · outbound

This paper cites CIMAT: A Compute -In-Memory Architecture for On - chip Training Based on Transpose SRAM Arrays,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators CIMAT: A Compute -In-Memory Architecture for On - chip Training Based on Transpose SRAM Arrays,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:07.959044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b107c6d-5b86-42a7-a8a4-0386de99444b · outbound

This paper cites PUMA: A Programmable Ultra -efficient Memristor - based Accelerator for Machine Learning Inference,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators PUMA: A Programmable Ultra -efficient Memristor - based Accelerator for Machine Learning Inference,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.158295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0f68bd-b4df-4fcd-bd3a-85db5961fd22 · outbound

This paper cites ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.285065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbae6f06-6f56-4014-9042-a89de1605acb · outbound

This paper cites ImageNet: A large-scale hierarchical image database,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators ImageNet: A large-scale hierarchical image database,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.443824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da686439-27b3-4adb-8e86-92a54aed2086 · outbound

This paper cites JESD235D JEDEC Standard, High Bandwidth Memory DRAM (HBM1, HBM2).

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators JESD235D JEDEC Standard, High Bandwidth Memory DRAM (HBM1, HBM2)

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.586864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5755ff-98c6-43c1-a279-8a180bd870b2 · outbound

This paper cites TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.712240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54e1c77-31e4-4b0d-993b-4fb4505d12f4 · outbound

This paper cites JESD209 - 5C, Low Power Double Data Rate (LPDDR) 5/5X.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators JESD209 - 5C, Low Power Double Data Rate (LPDDR) 5/5X

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:08.882133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b22016-40a9-4c08-9af1-04261c0cb70b · outbound

This paper cites Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures,.

ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T18:15:09.084823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.