ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs | Paper Citation Record

Observation a09784df-3e13-4932-ba5d-466559c41463 · outbound

This paper cites From words to watts: Benchmarking the energy costs of large language model inference,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs From words to watts: Benchmarking the energy costs of large language model inference,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.925222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36f9f220-f30e-4dbf-a12d-1e6393e44f54 · outbound

This paper cites Pim gpt a hybrid process in memory accelerator for autoregressive transformers,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Pim gpt a hybrid process in memory accelerator for autoregressive transformers,

Reference 2

Resolution: verified exact; doi, observed 2026-08-07T11:57:47.026315Z

Source-reported events for the cited work

correction dated 2025-03-04. Source: crossref record 10.1038/s44335-025-00019-3->10.1038/s44335-024-00004-2:correction, observed 2026-07-11T03:01:28.528393+00:00. This notice travels one citation hop only.

Observation 5d798424-fa30-4997-96ff-f49de3630333 · outbound

This paper cites Transpim: A memory- based acceleration via software-hardware co-design for transformer,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Transpim: A memory- based acceleration via software-hardware co-design for transformer,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.895306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 22725c9b-adf5-4960-9893-7fd24740735f · outbound

This paper cites Hardsea: Hybrid analog-reram clustering and digital-sram in-memory computing accelerator for dynamic sparse self-attention in transformer,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Hardsea: Hybrid analog-reram clustering and digital-sram in-memory computing accelerator for dynamic sparse self-attention in transformer,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.860023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 73981477-458f-4582-896c-1ae42ad9215b · outbound

This paper cites Efficient scaling of large language models with mixture of experts and 3d analog in-memory computing,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Efficient scaling of large language models with mixture of experts and 3d analog in-memory computing,

Reference 5

Resolution: verified exact; doi, observed 2026-08-07T11:57:46.977260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1eb82158-7cee-4b28-872c-33870549617a · outbound

This paper cites Paretoq: Scaling laws in extremely low-bit llm quantiza- tion,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Paretoq: Scaling laws in extremely low-bit llm quantiza- tion,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.378473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e695579-b066-4979-a643-dd4e8e27e1b1 · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.488313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe34546e-ff26-441d-a538-263c9d7a31ed · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.599535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 253ec4c4-16a3-42ab-a7ac-7cc987e12e89 · outbound

This paper cites BitNet a4.8: 4-bit Activations for 1-bit LLMs.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs BitNet a4.8: 4-bit Activations for 1-bit LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.713742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20725f29-f4e6-4938-9e28-a91f1ec39320 · outbound

This paper cites Site cim: Signed ternary computing-in-memory for ultra-low precision deep neural networks,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Site cim: Signed ternary computing-in-memory for ultra-low precision deep neural networks,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.819831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba2e3be2-9279-4898-aac7-d51d44be5baa · outbound

This paper cites Tim-dnn: Ternary in-memory accelerator for deep neural networks,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Tim-dnn: Ternary in-memory accelerator for deep neural networks,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.798868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90cec0f1-5372-4b86-8c5e-24104f7e3d5e · outbound

This paper cites A ternary neural net- work computing-in-memory processor with 16t1c bitcell architecture,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs A ternary neural net- work computing-in-memory processor with 16t1c bitcell architecture,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.762465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f8dd1ef8-5e42-499e-bea2-0170a9ed1fc3 · outbound

This paper cites A 2941-tops/w charge-domain 10t sram compute-in- memory for ternary neural network,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs A 2941-tops/w charge-domain 10t sram compute-in- memory for ternary neural network,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.723523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef936dc1-7f62-46a6-8186-60a31ecc8286 · outbound

This paper cites Drop-connect as a fault-tolerance approach for rram- based deep neural network accelerators,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Drop-connect as a fault-tolerance approach for rram- based deep neural network accelerators,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.689763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e2f951a1-59eb-49cf-8b30-d6e31430f1c9 · outbound

This paper cites Fault-tolerant training with on-line fault detection for rram-based neural computing systems,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Fault-tolerant training with on-line fault detection for rram-based neural computing systems,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.660640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7e2ae61-ffb1-4891-95b9-3fdb3cef104c · outbound

This paper cites Artificial Intelligence Index Report 2024,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Artificial Intelligence Index Report 2024,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.624595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 71439015-3b2a-4fe2-8125-f03cf554034c · outbound

This paper cites Wesco: Weight-encoded reliability and security co-design for in- memory computing systems,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Wesco: Weight-encoded reliability and security co-design for in- memory computing systems,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.583053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ca89d49a-93c4-4f5a-81b3-82bd5aa4543a · outbound

This paper cites Fault-free: A framework for analysis and mitigation of stuck-at-fault on realistic reram-based dnn accelerators,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Fault-free: A framework for analysis and mitigation of stuck-at-fault on realistic reram-based dnn accelerators,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.520378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ca28c12-fe5d-4b64-a0e2-7f3866f071ab · outbound

This paper cites Handling stuck-at- faults in memristor crossbar arrays using matrix transformations,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Handling stuck-at- faults in memristor crossbar arrays using matrix transformations,

Reference 19

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T11:57:47.332691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5419af5c-74f9-4411-bcee-d1b78ab7df43 · outbound

This paper cites Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:57:47.191434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36b0bafc-89f1-47ae-a9e7-752edb7f52dc · outbound

This paper cites Tfix: Exploiting the natural redundancy of ternary neural networks for fault tolerant in-memory vec- tor matrix multiplication,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Tfix: Exploiting the natural redundancy of ternary neural networks for fault tolerant in-memory vec- tor matrix multiplication,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.483107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 298b5d95-51db-4fb5-adc5-9e8540315966 · outbound

This paper cites Learning sparse & ternary neural networks with entropy-constrained trained ternarization (ec2t),.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Learning sparse & ternary neural networks with entropy-constrained trained ternarization (ec2t),

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.444064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c90bffd-0868-4ac8-a7ab-79414d863d25 · outbound

This paper cites FAT: An in-memory accelerator with fast addition for ternary weight neural networks,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs FAT: An in-memory accelerator with fast addition for ternary weight neural networks,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.410416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ac5c49f-73c1-4b71-9f72-752d2da58a51 · outbound

This paper cites Nonvolatile multistates memories for high-density data storage,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Nonvolatile multistates memories for high-density data storage,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.378902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 56ccd15c-c478-4f00-bc5a-dc9adf789779 · outbound

This paper cites Stuck-at fault tolerance in rram computing systems,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Stuck-at fault tolerance in rram computing systems,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.338894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 86d9fb43-5e29-4cc5-b217-d861b3957c2f · outbound

This paper cites Analog computing for AI sometimes needs correction by digital computing: Why and when,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Analog computing for AI sometimes needs correction by digital computing: Why and when,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.300120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef21ea70-0aef-4d73-b590-d81b55df3249 · outbound

This paper cites Rtn: Reparameterized ternary network,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Rtn: Reparameterized ternary network,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.266321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b7db6836-7844-4cd9-9ffd-a826f362e7b0 · outbound

This paper cites Rram defect modeling and failure analysis based on march test and a novel squeeze-search scheme,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Rram defect modeling and failure analysis based on march test and a novel squeeze-search scheme,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:46.734743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe754064-5a74-4645-9e38-f3aa48ed8ccc · outbound

This paper cites Bitnet b1.58-large,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Bitnet b1.58-large,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.191435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b9079f61-3b5a-415f-94f0-fbdcb35f1d25 · outbound

This paper cites Bitnet b1.58-3b,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Bitnet b1.58-3b,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.146481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42f14711-f4e0-4107-9954-cbed86d9b7af · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:46.768175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0545af-6a98-4e3d-9364-5954caf6a9d9 · outbound

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

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:46.776171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf42d4cf-ee22-4c9c-8591-450ea679cb13 · outbound

This paper cites A heterogeneous and programmable compute-in-memory accelerator architecture for analog-ai using dense 2-d mesh,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs A heterogeneous and programmable compute-in-memory accelerator architecture for analog-ai using dense 2-d mesh,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.106518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9470ae86-128b-41dc-94e8-7ef70bd6e2b3 · outbound

This paper cites [Online].

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs [Online]

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.061334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dc550eed-2373-4bc4-bd99-6e433c71249c · outbound

This paper cites A compact model for metal–oxide resistive random access memory with experiment verification,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs A compact model for metal–oxide resistive random access memory with experiment verification,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:48.018211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a2438fff-fae7-443d-a8b4-664d088e3dee · outbound

This paper cites Modeling and comparative analysis of hysteretic ferroelectric and anti-ferroelectric fets,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Modeling and comparative analysis of hysteretic ferroelectric and anti-ferroelectric fets,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.986017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cb4a0119-271f-4f94-8f26-0c9f4e295139 · outbound

This paper cites In-memory computing primitive for sensor data fusion in 28 nm hkmg fefet technology,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs In-memory computing primitive for sensor data fusion in 28 nm hkmg fefet technology,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.952491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 84edc028-2fb8-475a-9c15-9e0e19d3eac3 · outbound

This paper cites Ferroelectric thickness dependent domain interactions in fefets for memory and logic: A phase-field model based analysis,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Ferroelectric thickness dependent domain interactions in fefets for memory and logic: A phase-field model based analysis,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.914312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 438a3376-2a72-463e-9c4c-b33de9401453 · outbound

This paper cites Comparative evaluation of memory technologies for synaptic crossbar arrays – part i: Robustness-driven device-circuit co-design and system implications,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Comparative evaluation of memory technologies for synaptic crossbar arrays – part i: Robustness-driven device-circuit co-design and system implications,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.871478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8ccb9271-c6f9-416e-840e-385def08a216 · outbound

This paper cites Modeling and circuit analysis of interconnects with tas2 barrier/liner,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Modeling and circuit analysis of interconnects with tas2 barrier/liner,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.834533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d390667b-f017-40c7-8156-02cf75b98cb7 · outbound

This paper cites Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays -- Part I: Robustness-driven Device-Circuit Co-Design and System Implications.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays -- Part I: Robustness-driven Device-Circuit Co-Design and System Implications

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:57:47.077548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4be128a6-e4d5-40be-9a21-9cd4c8d6fbdb · outbound

This paper cites Dnn+neurosim: An end- to-end benchmarking framework for compute-in-memory accelerators with versatile device technologies,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Dnn+neurosim: An end- to-end benchmarking framework for compute-in-memory accelerators with versatile device technologies,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.760182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0b3f7ee5-c0dc-4bde-802d-d36f0a25d899 · outbound

This paper cites Interconnect performance and scaling strategy at 7 nm node,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Interconnect performance and scaling strategy at 7 nm node,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.797139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 17744cf9-0425-4b50-8bc0-9ec26e1c40e1 · outbound

This paper cites TernaryBERT: Distillation-aware ultra-low bit BERT,.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs TernaryBERT: Distillation-aware ultra-low bit BERT,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.722215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b5be39a-5636-4846-949c-46bf1ac4c993 · outbound

This paper cites Available: https://aclanthology.org/2020.emnlp-main.37/.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs Available: https://aclanthology.org/2020.emnlp-main.37/

Reference 521

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:47.674274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7de678e9-b426-4cae-a762-478ffff77f3d · outbound

This paper cites SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks.

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:45.925750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers