Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity | Paper Citation Record

Observation e04c12b8-768a-48bf-8c72-d7a9c200e3ab · outbound

This paper cites Deep residual learning for image recognition.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Deep residual learning for image recognition

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T16:31:31.838869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90788a1-870b-4582-bc21-72f8d91dc6a1 · outbound

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

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity An image is worth 16x16 words: Transformers for image recognition at scale

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:33.053740Z

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 8bfd9eba-4108-4f35-8eb3-af96db27c71b · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Training data-efficient image transformers & distillation through attention

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:33.042532Z

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 b384ea77-78b9-4652-8375-c46183243f87 · outbound

This paper cites Learning natural language inference with LSTM.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Learning natural language inference with LSTM

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:33.031249Z

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 2234f5c9-ba90-4719-9eae-9cd7a9dde428 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language un- derstanding.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Bert: Pre-training of deep bidirectional transformers for language un- derstanding

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:33.020591Z

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 cc1fbbda-e1a1-44bd-9fcb-d5122d021159 · outbound

This paper cites Improving language understanding by generative pre-training, 2018.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Improving language understanding by generative pre-training, 2018

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T16:31:31.862280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b719083e-947e-4423-bd35-a3ef0490b9da · outbound

This paper cites Language models are unsupervised multitask learners.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Language models are unsupervised multitask learners

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T16:31:31.866664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1161e376-a5cc-4256-ac0a-3bc66276bd29 · outbound

This paper cites GPT-3: Its nature, scope, limits, and consequences.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity GPT-3: Its nature, scope, limits, and consequences

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.996181Z

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 66382a18-cd10-44cf-bb7b-d892ce409c79 · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Llama 2: Open foundation and fine-tuned chat models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.985725Z

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 a9675045-9361-43cd-ab8f-1910437ffde4 · outbound

This paper cites Edge intelligence: Paving the last mile of artificial intelligence with edge computing.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Edge intelligence: Paving the last mile of artificial intelligence with edge computing

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.975716Z

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 b648bbe1-afbc-49d1-9472-bb691510e3cd · outbound

This paper cites Deep learning-based smart task assistance in wearable augmented reality.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Deep learning-based smart task assistance in wearable augmented reality

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.964653Z

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 f7849f37-329c-4886-b512-dc5cd074c452 · outbound

This paper cites Trager, Shahar Avin, Adrian Weller, Yoshua Bengio, and Diane Coyle.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Trager, Shahar Avin, Adrian Weller, Yoshua Bengio, and Diane Coyle

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.953440Z

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 c3bd30ca-d4d3-4afb-8e67-dc8a2ddb2a31 · outbound

This paper cites Scaling laws for neural language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Scaling laws for neural language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.942124Z

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 7df88feb-94ce-4b1e-9df9-f2c60edbbca2 · outbound

This paper cites Towards accurate and reliable energy measurement of NLP models, 2020.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Towards accurate and reliable energy measurement of NLP models, 2020

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.929999Z

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 0a0cb3f9-b2b1-4a5a-bd8a-5c27b47d1c4e · outbound

This paper cites Full stack optimization of transformer inference: a survey, 2023.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Full stack optimization of transformer inference: a survey, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.919496Z

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 59db84ae-6a48-4c30-8b99-181a764046fd · outbound

This paper cites A survey on deploying mobile deep learning applications: A systemic and technical perspective.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity A survey on deploying mobile deep learning applications: A systemic and technical perspective

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.907907Z

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 d7430a8d-a0b8-4cbf-908b-4bfa79dd676b · outbound

This paper cites Design possibilities and challenges of DNN models: a review on the perspective of end devices.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Design possibilities and challenges of DNN models: a review on the perspective of end devices

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.897053Z

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 c29ffecc-79ba-4832-a8b1-d0bd6e79ea32 · outbound

This paper cites Easyquant: Post-training quantization via scale optimization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Easyquant: Post-training quantization via scale optimization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.885182Z

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 5993e570-af8e-4457-a609-af745fa42785 · outbound

This paper cites Post-training quantization for vision transformer.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Post-training quantization for vision transformer

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.873271Z

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 41180117-4446-463f-a2a4-b30f9a9037d7 · outbound

This paper cites Brecq: Pushing the limit of post- training quantization by block reconstruction.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Brecq: Pushing the limit of post- training quantization by block reconstruction

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.862065Z

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 d68436e7-9abc-4b48-ab1a-efbcb4cc6d8c · outbound

This paper cites Aciq: Analytical clipping for integer quantization of neural networks.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Aciq: Analytical clipping for integer quantization of neural networks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.850628Z

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 ce342f80-75ab-4abb-88d4-8e2c0d59f7b5 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quan- tization for large language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Smoothquant: Accurate and efficient post-training quan- tization for large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.840366Z

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 5204b4a0-ec41-45f5-94df-f24db9b9393a · outbound

This paper cites Fq-vit: Post-training quantization for fully quantized vision transformer.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Fq-vit: Post-training quantization for fully quantized vision transformer

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.829674Z

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 0095c220-29bd-4e3d-bf13-73cff77aced6 · outbound

This paper cites Pd-quant: Post-training quantization based on prediction difference metric.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Pd-quant: Post-training quantization based on prediction difference metric

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.818553Z

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 fba57e6e-dda8-4f15-98d5-2f2d29ae7af0 · outbound

This paper cites Flexround: Learnable rounding based on element-wise division for post- training quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Flexround: Learnable rounding based on element-wise division for post- training quantization

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.806043Z

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 6a84a06c-57de-456d-89e3-971ff4f7230e · outbound

This paper cites Zeroq: A novel zero shot quantization framework.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Zeroq: A novel zero shot quantization framework

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.795478Z

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 49982629-7561-4433-86ad-f4c02d928a20 · outbound

This paper cites Repq-vit: Scale reparameterization for post-training quantization of vision transformers.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Repq-vit: Scale reparameterization for post-training quantization of vision transformers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.785298Z

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 dd883a39-a4f1-4e8e-8106-0dd41028cd8e · outbound

This paper cites Outlier suppression: Pushing the limit of low-bit transformer language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Outlier suppression: Pushing the limit of low-bit transformer language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.774467Z

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 40ea2c88-7924-4ee1-932a-2d0d9ecf31e7 · outbound

This paper cites Outlier suppression+: Accurate 13 quantization of large language models by equivalent and optimal shifting and scaling.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Outlier suppression+: Accurate 13 quantization of large language models by equivalent and optimal shifting and scaling

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.763046Z

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 57a9aad2-59c8-4e81-8372-98829c6b2d79 · outbound

This paper cites A white paper on neural network quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity A white paper on neural network quantization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.751589Z

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 b0da9461-3853-4247-87e1-36a9ade50205 · outbound

This paper cites Qllm: Accurate and efficient low-bitwidth quantization for large language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Qllm: Accurate and efficient low-bitwidth quantization for large language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.740534Z

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 4fdbf3a3-53e5-4d7d-9a9e-22aa6a59a09d · outbound

This paper cites Omniquant: Omnidirectionally calibrated quantization for large language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Omniquant: Omnidirectionally calibrated quantization for large language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.729939Z

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 ff2f412a-d4b8-4feb-96b4-439de599b1b1 · outbound

This paper cites Bitwave: Exploiting column-based bit-level sparsity for deep learning acceleration.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Bitwave: Exploiting column-based bit-level sparsity for deep learning acceleration

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.719450Z

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 49e17534-c7e4-4bb8-bf31-45428693d45c · outbound

This paper cites Cambricon-X: An accelerator for sparse neural networks.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Cambricon-X: An accelerator for sparse neural networks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.708612Z

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 77117f50-b13d-436b-a462-eebfc530e141 · outbound

This paper cites Sparse tensor core: Algorithm and hardware co-design for vector-wise sparse neural networks on modern gpus.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Sparse tensor core: Algorithm and hardware co-design for vector-wise sparse neural networks on modern gpus

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.698035Z

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 50e1bbc2-e84f-4021-995f-b6c30ed17679 · outbound

This paper cites Learning both weights and connections for efficient neural network.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Learning both weights and connections for efficient neural network

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.687677Z

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 9789f6a2-bfa1-469a-9463-0e44a06e5385 · outbound

This paper cites An algorithm–hardware co-optimized framework for accelerating n: M sparse transformers.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity An algorithm–hardware co-optimized framework for accelerating n: M sparse transformers

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.677720Z

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 89015e58-c894-4de6-ad02-46b6c2f025cb · outbound

This paper cites Energy-efficient risc-v-based vector processor for cache- aware structurally-pruned transformers.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Energy-efficient risc-v-based vector processor for cache- aware structurally-pruned transformers

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.667408Z

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 6790f1b7-640f-4d39-870a-4df868fc3784 · outbound

This paper cites Sparsity-Aware Memory Interface Architecture using Stacked XORNet Compression for Accelerating Pruned-DNN Models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Sparsity-Aware Memory Interface Architecture using Stacked XORNet Compression for Accelerating Pruned-DNN Models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.655804Z

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 e6238838-5648-4da4-9844-f0ac4d220c19 · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.644174Z

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 25081136-44db-4417-8069-ad26d11e3140 · outbound

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

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity I-bert: Integer-only bert quantization

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.633183Z

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 2903385a-1443-48ba-8e6d-f908bbedfbf9 · outbound

This paper cites Quantization and training of neural networks for efficient integer- arithmetic-only inference.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Quantization and training of neural networks for efficient integer- arithmetic-only inference

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.622619Z

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 fc3c6520-cd44-45b7-a179-b0897dbca04b · outbound

This paper cites Olive: Accelerating large language models via hardware-friendly outlier-victim pair quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Olive: Accelerating large language models via hardware-friendly outlier-victim pair quantization

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.611569Z

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 f83b911d-b665-4e16-979d-ad675a9d9112 · outbound

This paper cites Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.599558Z

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 5bb88209-dca5-4786-9240-b7a268f52e82 · outbound

This paper cites Gobo: Quantizing attention-based nlp models for low latency and energy efficient inference.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Gobo: Quantizing attention-based nlp models for low latency and energy efficient inference

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.588741Z

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 8c04b1fd-0224-4320-89e7-cc4ab2d901b5 · outbound

This paper cites OPTQ: Accurate quantization for generative pre-trained transformers.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity OPTQ: Accurate quantization for generative pre-trained transformers

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.577133Z

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 e5c03ecf-a69e-4b8b-9789-631e6016c952 · outbound

This paper cites Rptq: Reorder-based post-training quantization for large language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Rptq: Reorder-based post-training quantization for large language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.565780Z

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 634b04c6-26a9-4410-a650-d313566a33d7 · outbound

This paper cites Ant: Exploiting adaptive numerical data type for low-bit deep neural network quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Ant: Exploiting adaptive numerical data type for low-bit deep neural network quantization

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.555330Z

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 79aa2944-555b-4baf-ae12-f710febdcd69 · outbound

This paper cites Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.544732Z

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 bd50092d-1dba-443f-80ec-b159aa89f4a1 · outbound

This paper cites Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.534102Z

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 aa3e0fc1-2fe7-4bb8-81a9-f304bad395e4 · outbound

This paper cites Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.524020Z

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 0cea7cdb-2232-45a0-81c4-f6ff5b48b072 · outbound

This paper cites Qserve: W4a8kv4 quantization and system co-design for efficient llm serving.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Qserve: W4a8kv4 quantization and system co-design for efficient llm serving

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.513768Z

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 51f70004-47ee-4028-bdb8-7b7b586183a5 · outbound

This paper cites Sibia: Signed bit-slice architecture for dense dnn acceleration with slice-level sparsity exploitation.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Sibia: Signed bit-slice architecture for dense dnn acceleration with slice-level sparsity exploitation

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.503030Z

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 56a9623b-5001-4aab-b22f-c82709f654d2 · outbound

This paper cites Non-blocking simultaneous multithread- ing: Embracing the resiliency of deep neural networks.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Non-blocking simultaneous multithread- ing: Embracing the resiliency of deep neural networks

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.491390Z

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 8a13bff6-78cb-4822-952f-cb2d31b1d80b · outbound

This paper cites Hnpu-v1: An adaptive dnn train- ing processor utilizing stochastic dynamic fixed-point and active bit- precision searching.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Hnpu-v1: An adaptive dnn train- ing processor utilizing stochastic dynamic fixed-point and active bit- precision searching

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.479835Z

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 074b8873-c187-4f26-8bc2-d1c04bb80a5e · outbound

This paper cites Lutein: Dense-sparse bit-slice architec- ture with radix-4 lut-based slice-tensor processing units.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Lutein: Dense-sparse bit-slice architec- ture with radix-4 lut-based slice-tensor processing units

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.468490Z

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 0b8c9e7d-973d-4673-b72c-1390c9c9dc59 · outbound

This paper cites Embedded deep neural network processing: Algorithmic and processor techniques bring deep learning to iot and edge devices.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Embedded deep neural network processing: Algorithmic and processor techniques bring deep learning to iot and edge devices

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.455351Z

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 a331e273-d913-4d5d-9933-016dc5a3cffe · outbound

This paper cites MEISSA: Multi- plying matrices efficiently in a scalable systolic architecture.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity MEISSA: Multi- plying matrices efficiently in a scalable systolic architecture

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.443157Z

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 978cfb4e-4964-43cb-9566-322da23c504d · outbound

This paper cites A 95.6-TOPS/W deep learning inference accelerator with per- vector scaled 4-bit quantization in 5 nm.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity A 95.6-TOPS/W deep learning inference accelerator with per- vector scaled 4-bit quantization in 5 nm

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.431646Z

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 e62f800c-72d4-4af0-a5ce-57cb5f2977b1 · outbound

This paper cites Opt: Open pre-trained transformer language models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Opt: Open pre-trained transformer language models

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.418355Z

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 c7dc9894-bc98-4a06-bbd4-3fbb790cce72 · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Llama 3.2: Revolutionizing edge ai and vision with open, customizable models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.406023Z

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 8fdd26bf-7fb9-4840-8bb4-82b178ca8be9 · outbound

This paper cites Xtc: Extreme compression for pre-trained transformers made simple and efficient.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Xtc: Extreme compression for pre-trained transformers made simple and efficient

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.394625Z

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 e3a6ac3e-47cc-4389-bdf4-b8a8f5600b2e · outbound

This paper cites Energy-efficient neural network accelerator based on outlier-aware low-precision com- putation.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Energy-efficient neural network accelerator based on outlier-aware low-precision com- putation

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.381912Z

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 4bd9bbc2-85ca-4f2b-ba30-924f3c056d4a · outbound

This paper cites Drq: dynamic region-based quan- tization for deep neural network acceleration.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Drq: dynamic region-based quan- tization for deep neural network acceleration

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.369914Z

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 b542d448-8f9b-48fb-bc10-3abdee46b9ed · outbound

This paper cites FIGNA: Integer Unit-Based Accelerator Design for FP-INT GEMM Preserving Numerical Accuracy.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity FIGNA: Integer Unit-Based Accelerator Design for FP-INT GEMM Preserving Numerical Accuracy

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.357924Z

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 b5c8c6f5-96a5-4207-8834-2f1a454f77c6 · outbound

This paper cites Loss aware post- training quantization.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Loss aware post- training quantization

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.345973Z

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 2ee21d5c-4e5a-4be4-95d3-11282bd14e09 · outbound

This paper cites Efficient processing of deep neural networks: A tutorial and survey.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Efficient processing of deep neural networks: A tutorial and survey

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.334776Z

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 c8bd2389-5b56-4aff-b20b-6c9009612778 · outbound

This paper cites A survey of quantization methods for efficient neural network inference.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity A survey of quantization methods for efficient neural network inference

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.322666Z

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 eab0af6c-aa0d-4152-889f-6b6673375f0b · outbound

This paper cites Accurate post training quantization with small calibration sets.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Accurate post training quantization with small calibration sets

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.309863Z

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 0803260e-1012-4678-8727-52309e0bc83f · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Understanding the difficulty of training deep feedforward neural networks

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.298369Z

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 4aa91389-e284-42d9-93c8-04dcb4a23a58 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.286334Z

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 1ab38065-fb4f-4678-9031-2a51473f2054 · outbound

This paper cites Efficient backprop.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Efficient backprop

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.274183Z

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 e67c3b2f-20f6-4da1-909f-c64c5a91587e · outbound

This paper cites Probact: A probabilistic activation function for deep neural networks.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Probact: A probabilistic activation function for deep neural networks

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.262222Z

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 038f875b-47ef-487e-b0d7-4a40fb1696b4 · outbound

This paper cites Bayesian learning for neural networks , volume 118.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Bayesian learning for neural networks , volume 118

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T16:31:32.125769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87bbf317-4a1e-4715-a9ce-18cb223144d7 · outbound

This paper cites GLUE: A multi-task benchmark and analysis platform for natural language understanding.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity GLUE: A multi-task benchmark and analysis platform for natural language understanding

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.242103Z

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 3be931ab-bca9-41f8-ab6f-e60fead64eff · outbound

This paper cites Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.228932Z

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 56982ad2-4ef4-496e-bc47-cef1e4a25b49 · outbound

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

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Imagenet: A large-scale hierarchical image database

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T16:31:32.137521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904a7355-8dca-473b-b5a8-05e8219d05a1 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.207819Z

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 cf4266f5-55bb-403d-9626-006423a0f2a5 · outbound

This paper cites CACTI 7: New tools for interconnect exploration in innovative off-chip memories.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity CACTI 7: New tools for interconnect exploration in innovative off-chip memories

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.196169Z

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 8b12c13a-f926-4453-b022-febc207c7e46 · outbound

This paper cites Pointer sentinel mixture models.

Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Pointer sentinel mixture models

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:31:32.183584Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers