Paper Citation Record · LEDGER

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC

As of 13 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2411.13050.

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

pith.paper-citation-record.v1
2411.13050 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T17:00:08.776106Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

23 of 23 outbound references displayed

verified exact0
verified fuzzy23
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d5beb75b-a4ae-466c-8e88-3b1c90ca93c1 · outbound

This paper cites ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.279000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 05a35039-d8bb-4b0b-af30-b03dcbfcc846 · outbound

This paper cites Spatten: Efficient sparse attention architecture with cascade token and head pruning,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Spatten: Efficient sparse attention architecture with cascade token and head pruning,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.260413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d5ee5cd9-a46f-46fd-84fd-580934c82eb6 · outbound

This paper cites A length adaptive algorithm-hardware co-design of transformer on fpga through sparse attention and dynamic pipelining,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC A length adaptive algorithm-hardware co-design of transformer on fpga through sparse attention and dynamic pipelining,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.235264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ec57079f-03c7-4621-842a-c21fe309cdae · outbound

This paper cites X-former: In- memory acceleration of transformers,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC X-former: In- memory acceleration of transformers,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.217978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 09a3ee38-d53c-4b1b-a954-7ba1408e22c3 · outbound

This paper cites DNN+ NeuroSim V2. 0: An end-to-end benchmarking framework for compute-in-memory accelerators for on-chip training,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC DNN+ NeuroSim V2. 0: An end-to-end benchmarking framework for compute-in-memory accelerators for on-chip training,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.200910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9c44c675-dbd7-4906-9637-7fed633daee7 · outbound

This paper cites A 16K current- based 8T SRAM compute-in-memory macro with decoupled read/write and 1-5bit column ADC,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC A 16K current- based 8T SRAM compute-in-memory macro with decoupled read/write and 1-5bit column ADC,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.183539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e32f0d14-afd0-484d-aa4b-016b36a49460 · outbound

This paper cites Softermax: Hardware/software co-design of an efficient softmax for transformers,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Softermax: Hardware/software co-design of an efficient softmax for transformers,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.164192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3434807a-f742-4b0b-99db-81f0702df82e · outbound

This paper cites Base-2 softmax function: Suitability for training and efficient hardware implementation,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Base-2 softmax function: Suitability for training and efficient hardware implementation,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.144265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f3c96f54-3684-49a3-9264-85abc125bdb7 · outbound

This paper cites Hardware implementation of the exponential function using Taylor series,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Hardware implementation of the exponential function using Taylor series,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.126194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7addbd61-8e0a-410f-a505-3bb78769c15e · outbound

This paper cites On the Computational Power of Winner-Take-All,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC On the Computational Power of Winner-Take-All,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.105269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b323bf25-0ab8-4c0c-809f-ad597ae93136 · outbound

This paper cites Vitality: Unifying low-rank and sparse approximation for vision transformer acceleration with a linear taylor attention,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Vitality: Unifying low-rank and sparse approximation for vision transformer acceleration with a linear taylor attention,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.083674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e9981a9e-0d3d-41be-827c-d58ca5e0799f · outbound

This paper cites I-bert: Integer- only bert quantization,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC I-bert: Integer- only bert quantization,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.061394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b4b819c0-3f10-4601-831f-f17159667240 · outbound

This paper cites Efficient softmax hardware architecture for deep neural networks,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Efficient softmax hardware architecture for deep neural networks,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.038840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 28ff3607-11eb-47e3-8186-6e24b9f0c5fc · outbound

This paper cites TranCIM: Full- digital bitline-transpose CIM-based sparse transformer accelerator with pipeline/parallel reconfigurable modes,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC TranCIM: Full- digital bitline-transpose CIM-based sparse transformer accelerator with pipeline/parallel reconfigurable modes,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:09.014896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f6e8666b-caeb-477c-b886-41659b8a04c9 · outbound

This paper cites Challenges and trends of SRAM-based computing-in-memory for AI edge devices,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Challenges and trends of SRAM-based computing-in-memory for AI edge devices,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.988769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 32adab4c-4da4-4659-a4ff-5667ad5bcc13 · outbound

This paper cites A 240×180 130 db 3 µs latency global shutter spatiotemporal vision sensor,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC A 240×180 130 db 3 µs latency global shutter spatiotemporal vision sensor,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.968599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4bc3ae42-b785-4323-a7e3-ecc091a97d89 · outbound

This paper cites Hardware-aware softmax approximation for deep neural networks,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Hardware-aware softmax approximation for deep neural networks,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.949930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0b0a0c90-c364-4d71-830b-661cbcbc4b34 · outbound

This paper cites Memristor-based edge computing of blaze block for image recognition,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Memristor-based edge computing of blaze block for image recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.929432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 751eeaba-c043-47ba-b9af-387b5a77607d · outbound

This paper cites 19.7 A 16Gb ReRAM with 200MB/s write and 1GB/s read in 27nm technology,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC 19.7 A 16Gb ReRAM with 200MB/s write and 1GB/s read in 27nm technology,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.906167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 534a638a-a083-4fb3-8227-a8ac52f101c9 · outbound

This paper cites 90 nm 32×32 bit Tunneling SRAM Memory Array With 0.5 ns Write Access Time, 1 ns Read Access Time and 0.5 V Operation,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC 90 nm 32×32 bit Tunneling SRAM Memory Array With 0.5 ns Write Access Time, 1 ns Read Access Time and 0.5 V Operation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.885306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c1fdb7c5-e56a-45ac-9a88-ebcc738b5a30 · outbound

This paper cites Tron: Transformer neural network acceleration with non-coherent silicon photonics,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Tron: Transformer neural network acceleration with non-coherent silicon photonics,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.863894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ca4cc5dd-416e-4ca3-894f-f142ce63a8f5 · outbound

This paper cites ELSA: Hardware-software co-design for efficient, lightweight self-attention mechanism in neural networks,.

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC ELSA: Hardware-software co-design for efficient, lightweight self-attention mechanism in neural networks,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.843300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d09f5fb0-ff5b-4cd0-b045-cec722b13f3e · outbound

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

Topkima-Former: Low-energy, Low-Latency Inference for Transformers using top-k In-memory ADC Hardsea: Hybrid analog-reram clustering and digital-sram in-memory computing accelera- tor for dynamic sparse self-attention in transformer,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:00:08.822501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.