CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge | Paper Citation Record

Observation 3cc23a94-ad17-4c6c-92a8-25b94e6a0924 · outbound

This paper cites Rewind: A better way to search your digital life, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Rewind: A better way to search your digital life, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.361870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 897b39d5-ddef-4220-98f7-a17bea375f7f · outbound

This paper cites An open-source framework for autonomous soc design with analog block generation.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge An open-source framework for autonomous soc design with analog block generation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.442444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3fd116f-ad1c-453a-82d5-acdf9a3eced5 · outbound

This paper cites The illustrated gpt-2 (visualizing trans- former language models).Jalammar.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge The illustrated gpt-2 (visualizing trans- former language models).Jalammar

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.637143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21b22ec-6027-4945-98ae-68596982659f · outbound

This paper cites LLM in a flash: Efficient Large Language Model Inference with Limited Memory.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.786243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 292e48e6-24ab-42f0-8ff2-9c9d8af50a64 · outbound

This paper cites Claude: A family of ai models, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Claude: A family of ai models, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.817687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d336f0-d870-4a8c-bd09-1d635053d3fa · outbound

This paper cites Apple intelligence.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Apple intelligence

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.972873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff3fe49a-584b-442e-8c18-875471b3ad65 · outbound

This paper cites Apple siri: Virtual assistant, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Apple siri: Virtual assistant, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.980912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c47924d-2585-4a07-af14-b99b5b35ee21 · outbound

This paper cites SliceGPT: Compress Large Language Models by Deleting Rows and Columns.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.984809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37fd1495-cc8f-4f20-9b83-914429bddfe3 · outbound

This paper cites 25.1 a fully synthesizable distributed and scalable all-digital ldo in 10nm cmos.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge 25.1 a fully synthesizable distributed and scalable all-digital ldo in 10nm cmos

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:29.988251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7146166-892c-4f84-bf31-4346bce7de12 · outbound

This paper cites {NeuOS}: A {Latency- Predictable}{Multi-Dimensional} optimization frame- work for {DNN-driven} autonomous systems.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge {NeuOS}: A {Latency- Predictable}{Multi-Dimensional} optimization frame- work for {DNN-driven} autonomous systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.033790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e0b18a-e656-4515-b77f-133a1022c919 · outbound

This paper cites Bender, Timnit Gebru, Angelina McMillan- Major, and Shmargaret Shmitchell.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Bender, Timnit Gebru, Angelina McMillan- Major, and Shmargaret Shmitchell

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.037121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 095e4547-b476-4382-8ec6-99492013f2b9 · outbound

This paper cites PIQA: reasoning about physical commonsense in natural language.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge PIQA: reasoning about physical commonsense in natural language

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.040052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ceb2af1-898b-4870-97cc-203e0d496c8a · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge On the Opportunities and Risks of Foundation Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.043082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da7612c2-af60-4652-a382-cd1498fb8143 · outbound

This paper cites An estimate of an upper bound for the entropy of english.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge An estimate of an upper bound for the entropy of english

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.046628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f5a3be4-0875-4749-9f67-3d1821e7fdb4 · outbound

This paper cites an unresolved cited work.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.049551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e89f9a1-9fd3-4cf6-a3df-6948022d7d73 · outbound

This paper cites A fre- quency compensation scheme for ldo voltage regula- tors.IEEE Transactions on Circuits and Systems I: Regular Papers, 51(6):1041–1050, 2004.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A fre- quency compensation scheme for ldo voltage regula- tors.IEEE Transactions on Circuits and Systems I: Regular Papers, 51(6):1041–1050, 2004

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.052735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3838fe1c-f4e0-4005-9923-c6954dca22e9 · outbound

This paper cites Bge m3-embedding: Multi- lingual, multi-functionality, multi-granularity text em- beddings through self-knowledge distillation, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Bge m3-embedding: Multi- lingual, multi-functionality, multi-granularity text em- beddings through self-knowledge distillation, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.055847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ea6e24-12bb-45ea-8dfd-9c691b9bacf5 · outbound

This paper cites Op- timizing energy efficiency of browsers in energy-aware scheduling-enabled mobile devices.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Op- timizing energy efficiency of browsers in energy-aware scheduling-enabled mobile devices

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.058717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 872e40fe-bb1c-4730-8535-aacdb0088def · outbound

This paper cites an unresolved cited work.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.061530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a962fe-6853-4879-b4d7-000581fb08d1 · outbound

This paper cites ML.ENERGY leaderboard.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge ML.ENERGY leaderboard

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.064298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45893bdb-be31-49d0-9e61-c067e8026f8c · outbound

This paper cites Hechtman, Trevor Cai, Sebastian Borgeaud, George van den Driessche, Eliza Ruther- ford, Tom Hennigan, Matthew J.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Hechtman, Trevor Cai, Sebastian Borgeaud, George van den Driessche, Eliza Ruther- ford, Tom Hennigan, Matthew J

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.066924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc02c78-a21c-4b6f-aad3-4c110cdd1624 · outbound

This paper cites Boolq: Exploring the surprising difficulty of natural yes/no questions.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.069780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ffa5f7-1128-4cae-b93d-847c1d46ee0a · outbound

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

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.072546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b4ae27-2128-4ce2-a496-5b21c0ba3f82 · outbound

This paper cites Track and reduce co2 emissions from your computing.https://codecarbon.io/, 2023.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Track and reduce co2 emissions from your computing.https://codecarbon.io/, 2023

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.075288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 796f6d98-7a46-477d-a3bb-58d44d4844a3 · outbound

This paper cites Llama 2: Inferencing on a single gpu.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Llama 2: Inferencing on a single gpu

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.077959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604a50a1-60b3-4f03-9137-e059d4a4020c · outbound

This paper cites Llm.int8(): 8-bit matrix multiplication for transformers at scale.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Llm.int8(): 8-bit matrix multiplication for transformers at scale

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.081219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64368e54-f293-4069-ae4d-d84d825cc5ef · outbound

This paper cites Pruner- zero: Evolving symbolic pruning metric from scratch for large language models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Pruner- zero: Evolving symbolic pruning metric from scratch for large language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.083937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f2949f7-6d06-4034-a4f3-653ce46f9761 · outbound

This paper cites User-aware frame rate man- agement in android smartphones.ACM Trans.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge User-aware frame rate man- agement in android smartphones.ACM Trans

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.086587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041a2a81-ab56-44b6-b9db-db536e6254ae · outbound

This paper cites Bradley Chen, and Margo I.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Bradley Chen, and Margo I

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.089369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9583e905-eaa1-44e8-9835-575700d5f855 · outbound

This paper cites Depgraph: Towards any struc- tural pruning.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Depgraph: Towards any struc- tural pruning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.092261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de9f1fce-d890-4ca5-b48d-1f823c8af701 · outbound

This paper cites Gpt-3: Its nature, scope, limits, and consequences.Minds and Machines, 30:681–694, 2020.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Gpt-3: Its nature, scope, limits, and consequences.Minds and Machines, 30:681–694, 2020

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.095081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb189c35-5f9d-45bd-9114-056fddd214de · outbound

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

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Sparsegpt: Massive language models can be accurately pruned in one- shot

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.097575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55ce9d8-21c3-4720-9cd7-b87bd6aeaafd · outbound

This paper cites Beam search strategies for neural machine translation.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Beam search strategies for neural machine translation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.100144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69364cba-1976-45da-a39a-b3df3fead741 · outbound

This paper cites Drive like a human: Rethinking autonomous driving with large language models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Drive like a human: Rethinking autonomous driving with large language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.103379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c860af55-87db-4946-83fd-00f015302dff · outbound

This paper cites Openllama: An open reproduction of llama.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Openllama: An open reproduction of llama

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.106009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d77d22-77ec-4e93-8ea0-00aa98e048e2 · outbound

This paper cites Mahoney, and Kurt Keutzer.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Mahoney, and Kurt Keutzer

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.108661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f17d1f1f-d07a-4a6d-8309-55bc9119823b · outbound

This paper cites GitHub Copilot: Your AI pair programmer.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge GitHub Copilot: Your AI pair programmer

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.111229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f64bbe97-1e6f-42d7-84fa-8450a8f60850 · outbound

This paper cites Goodfellow, Yoshua Bengio, and Aaron C.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Goodfellow, Yoshua Bengio, and Aaron C

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.114160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b3382f0-4364-4c1c-9d32-74e10676352e · outbound

This paper cites Google assistant, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Google assistant, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.117045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f2bac2c-c034-4d83-a651-89bceb96265b · outbound

This paper cites Ml kit smart reply, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Ml kit smart reply, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.119676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cf2c75c-bcf0-4cef-ae89-6262d90269b6 · outbound

This paper cites Minillm: Knowledge distillation of large language models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Minillm: Knowledge distillation of large language models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.122280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48647cfb-269f-4b74-8277-6b6b16bd0223 · outbound

This paper cites Mistify: Au- tomating DNN model porting for on-device inference at the edge.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Mistify: Au- tomating DNN model porting for on-device inference at the edge

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.125464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abdec490-9ec9-40c3-a893-4c638a35bc0f · outbound

This paper cites A reconfigurable floating- point compute-in-memory with analog exponent pre- processes.IEEE Solid-State Circuits Letters, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A reconfigurable floating- point compute-in-memory with analog exponent pre- processes.IEEE Solid-State Circuits Letters, 2024

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.128612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7239543f-7a02-46bb-af68-8a51fc5d189c · outbound

This paper cites A 28nm 314.6 tl- fops/w reconfigurable floating-point analog compute- in-memory macro with exponent approximation and two-stage sharing td-adc.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A 28nm 314.6 tl- fops/w reconfigurable floating-point analog compute- in-memory macro with exponent approximation and two-stage sharing td-adc

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.131269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a24dfbc-92cc-4df8-b7c9-58ab85a82f62 · outbound

This paper cites Channel pruning for accelerating very deep neural networks.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Channel pruning for accelerating very deep neural networks

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.133896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b98e9c1-f26a-465a-a724-b3405b37e79f · outbound

This paper cites Measuring massive multitask language under- standing.Proceedings of the International Conference on Learning Representations (ICLR), 2021.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Measuring massive multitask language under- standing.Proceedings of the International Conference on Learning Representations (ICLR), 2021

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.136923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1be03e-9e80-478b-a717-7833c3102880 · outbound

This paper cites Variation- aware dynamic voltage/frequency scaling.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Variation- aware dynamic voltage/frequency scaling

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.139632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3076f9ce-ad6b-40d4-a7f6-57c4a6c43403 · outbound

This paper cites Enright Jerger.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Enright Jerger

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.144325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be61a365-d8c8-4190-8266-e7c23b044d80 · outbound

This paper cites Long short- term memory.Neural Comput., 9(8):1735–1780, 1997.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Long short- term memory.Neural Comput., 9(8):1735–1780, 1997

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.147171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da47bce-206d-4cbc-bf0d-15b02dbbbcda · outbound

This paper cites The curious case of neural text degener- ation.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge The curious case of neural text degener- ation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.150467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 769eb812-4ae8-4723-981d-74af0549f181 · outbound

This paper cites An all-digital phase-locked loop (adpll)-based clock re- covery circuit.IEEE Journal of Solid-State Circuits, 34(8):1063–1073, 1999.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge An all-digital phase-locked loop (adpll)-based clock re- covery circuit.IEEE Journal of Solid-State Circuits, 34(8):1063–1073, 1999

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.153381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e8d0a00-0354-4f0b-b5f2-80aecb7af26f · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge LoRA: Low-Rank Adaptation of Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.156139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e817ff94-a586-40ec-b214-43b09edf3e5e · outbound

This paper cites CAMA: energy and memory efficient automata pro- cessing in content-addressable memories.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge CAMA: energy and memory efficient automata pro- cessing in content-addressable memories

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.159598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad978e9-5856-4fc0-bbdc-2241e8622759 · outbound

This paper cites New solutions on llm acceleration, optimization, and application.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge New solutions on llm acceleration, optimization, and application

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.162218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4046c736-b798-4d42-bbf3-8fc7fd4dfbd2 · outbound

This paper cites Quantized neural networks: Training neural networks with low precision weights and activations.Journal of Machine Learning Research, 18(187):1–30, 2018.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Quantized neural networks: Training neural networks with low precision weights and activations.Journal of Machine Learning Research, 18(187):1–30, 2018

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.164863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44aefa9-87c3-44f0-9c7d-885b1066a2ea · outbound

This paper cites Transformers documentation, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Transformers documentation, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.167284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd6a8791-f9bb-4329-98a7-ca39f72f9408 · outbound

This paper cites Just-in-time quan- tization with processing-in-memory for efficient ml training, 2023.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Just-in-time quan- tization with processing-in-memory for efficient ml training, 2023

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.170049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b91761-3cec-42f8-afd2-f5ed8fe933ca · outbound

This paper cites Mem: Your ai-powered assistant, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Mem: Your ai-powered assistant, 2024

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.172888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ae7c0b3-7caf-4ebf-8247-e6c83b4ee226 · outbound

This paper cites Jacobs, Michael I.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Jacobs, Michael I

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.175585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4277b1f4-5a03-4635-a0e8-8f9341c6abf5 · outbound

This paper cites LLM Performance Predictors are good initializers for Architecture Search.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge LLM Performance Predictors are good initializers for Architecture Search

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.178185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba7c83e-72ad-4c44-a7ee-3a26fcd32dd4 · outbound

This paper cites Robot control using llama: Bridging ai and robotics.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Robot control using llama: Bridging ai and robotics

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.181453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1b9f69-d1c5-48c1-91d7-7e49efbd5bae · outbound

This paper cites Reinforcement learning: A survey.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Reinforcement learning: A survey

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.184097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6b9963e-b9fd-4107-9ffc-84269b40d97d · outbound

This paper cites Scaling Laws for Neural Language Models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Scaling Laws for Neural Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.186985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2b5ecd-04d7-45cd-92e9-9f66ec8858a7 · outbound

This paper cites The breakthrough memory solutions for improved performance on LLM inference.IEEE Micro, 44(3):40–48, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge The breakthrough memory solutions for improved performance on LLM inference.IEEE Micro, 44(3):40–48, 2024

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.189680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee029fc-4609-43f4-acf9-f06ae3e5facb · outbound

This paper cites an unresolved cited work.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Unresolved cited work

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.192366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf5eddd-c825-4b65-be80-2450cca854f1 · outbound

This paper cites Enhancing energy efficiency of multimedia applications in heterogeneous mobile multi-core pro- cessors.IEEE Trans.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Enhancing energy efficiency of multimedia applications in heterogeneous mobile multi-core pro- cessors.IEEE Trans

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.195212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee46a44-a1a5-448b-a0a4-d3304c65b046 · outbound

This paper cites A novel gpu power model for accurate smartphone power break- down.ETRI journal, 37(1):157–164, 2015.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A novel gpu power model for accurate smartphone power break- down.ETRI journal, 37(1):157–164, 2015

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.198205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86b60bfc-362f-4f65-8a48-0116df482eed · outbound

This paper cites A survey on recent os-level energy management tech- niques for mobile processing units.IEEE Trans.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A survey on recent os-level energy management tech- niques for mobile processing units.IEEE Trans

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.200853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39b6851-d81f-407a-9acb-e2da44f62b94 · outbound

This paper cites Autoscale: Energy efficiency optimization for stochastic edge in- ference using reinforcement learning.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Autoscale: Energy efficiency optimization for stochastic edge in- ference using reinforcement learning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.203498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83517662-138f-4b16-a548-541351317bda · outbound

This paper cites InProceedings of the Fourteenth EuroSys Conference 2019, pages 1–15, 2019.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge InProceedings of the Fourteenth EuroSys Conference 2019, pages 1–15, 2019

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.206434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 408bd45e-875e-4fbf-9849-faeb181c09ed · outbound

This paper cites Distillm: Towards streamlined distillation for large language models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Distillm: Towards streamlined distillation for large language models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.209192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef5cbf70-b35e-42c5-a755-0304a781186f · outbound

This paper cites Resnet 50.Convolu- tional neural networks with swift for tensorflow: image recognition and dataset categorization, pages 63–72, 2021.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Resnet 50.Convolu- tional neural networks with swift for tensorflow: image recognition and dataset categorization, pages 63–72, 2021

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.212076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f794a6a5-a485-4ecc-afbf-392b83569178 · outbound

This paper cites Automatic domain-specific soc design for autonomous unmanned aerial vehicles.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Automatic domain-specific soc design for autonomous unmanned aerial vehicles

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.215564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd950b1a-20b4-48bc-8374-9fbc7b8b3643 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Efficient memory management for large language model serving with pagedattention

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.221498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed56dd15-8d16-4366-9676-5900aa6c51d3 · outbound

This paper cites Deep learning.nature, 521(7553):436–444, 2015.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Deep learning.nature, 521(7553):436–444, 2015

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.224331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69cebccd-b948-40af-afd5-fdc2c4638e23 · outbound

This paper cites On-chip memory technology design space explorations for mobile deep neural network ac- celerators.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge On-chip memory technology design space explorations for mobile deep neural network ac- celerators

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.227272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e1ddf1c-7d40-4158-a804-d0e42df8fa37 · outbound

This paper cites Energydx: Diag- nosing energy anomaly in mobile apps by identifying the manifestation point.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Energydx: Diag- nosing energy anomaly in mobile apps by identifying the manifestation point

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.230317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6dc3b1-2e9c-4e64-b001-e5d0b9c9fdb9 · outbound

This paper cites Deep Reinforcement Learning: An Overview.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Deep Reinforcement Learning: An Overview

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.233137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d60f56d-b849-4140-a9e7-34fe8f407d3e · outbound

This paper cites From system 1 to system 2: A survey of reasoning large language models, 2025.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge From system 1 to system 2: A survey of reasoning large language models, 2025

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.236152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bf5fe12-fd98-4833-86a1-03a882af4dd2 · outbound

This paper cites BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:20:30.967973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1ebb0ba8-a885-4001-b269-92f25beac8d0 · outbound

This paper cites an unresolved cited work.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Unresolved cited work

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.241803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4280d027-617c-4a5a-bd68-8ef290974005 · outbound

This paper cites Par- rot: Efficient serving of llm-based applications with semantic variable.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Par- rot: Efficient serving of llm-based applications with semantic variable

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.244455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8415a56a-8d5e-4c2f-ab47-0708dbf0f757 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.250265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8ff174-7f99-4c6e-ae28-94630d0ee829 · outbound

This paper cites A rein- forcement learning-based power management frame- work for green computing data centers.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A rein- forcement learning-based power management frame- work for green computing data centers

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.253352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 059d0a55-a48b-492c-88cb-8aece664d9b8 · outbound

This paper cites A weak puf-assisted strong PUF with inherent immunity to modeling attacks and ultra-low BER.IEEE Trans.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge A weak puf-assisted strong PUF with inherent immunity to modeling attacks and ultra-low BER.IEEE Trans

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.256232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c8c989-53c6-4d68-8751-493ecdc5f901 · outbound

This paper cites Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.ACM Comput.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.ACM Comput

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.259016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc9831d2-69bb-420a-bb53-fa0af3891423 · outbound

This paper cites Optimizing LLM Queries in Relational Data Analytics Workloads.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Optimizing LLM Queries in Relational Data Analytics Workloads

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.261857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c13187-fbe6-45f1-a899-603fbd6808fd · outbound

This paper cites P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.265155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e8bf18e-2803-44d9-815e-950769ad6970 · outbound

This paper cites S2ta: Exploiting structured sparsity for energy-efficient mobile cnn acceleration.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge S2ta: Exploiting structured sparsity for energy-efficient mobile cnn acceleration

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.268065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc06d880-bfde-4b77-a791-4d4d3dfe2413 · outbound

This paper cites Deja vu: Contextual sparsity for efficient llms at inference time.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Deja vu: Contextual sparsity for efficient llms at inference time

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.270805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de46390-2a91-4b0f-b3cf-42d3ec200c22 · outbound

This paper cites Prediction-guided performance-energy trade-off for in- teractive applications.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Prediction-guided performance-energy trade-off for in- teractive applications

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.273473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7497c9fe-741d-4040-8bf4-82b39c4554a3 · outbound

This paper cites Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.276218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c914c224-035c-4e1c-aa41-954e5254ae86 · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.278863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79bf636c-b388-40a6-b286-26ac92fe6ea4 · outbound

This paper cites Pointer sentinel mixture models.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Pointer sentinel mixture models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.281679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c2c25e-8a62-44d0-b1a0-e89445234836 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Gemma: Open Models Based on Gemini Research and Technology

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:30.284503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83756a73-5010-41ed-8ba1-e7deb2c5c203 · outbound

This paper cites Your Everyday AI Companion | Microsoft Bing.https://www.bing.com/new.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Your Everyday AI Companion | Microsoft Bing.https://www.bing.com/new

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:20:31.575245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d61d069-39b8-4c12-9e0e-9c70e9469066 · outbound

This paper cites Azure cognitive services - text analytics: Smart reply, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Azure cognitive services - text analytics: Smart reply, 2024

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:20:31.564613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9c879a7c-19b0-46e7-b8b8-44270946c878 · outbound

This paper cites Deepspeed: Advancing the science of ai through efficient training of large models, 2024.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Deepspeed: Advancing the science of ai through efficient training of large models, 2024

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:20:31.554368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2072150f-84ce-4f0b-a638-25af384b7116 · outbound

This paper cites Can a suit of armor conduct electricity? A new dataset for open book question answering.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Can a suit of armor conduct electricity? A new dataset for open book question answering

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:20:31.543370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c896b732-803f-40d2-8d70-e7656d596dcb · outbound

This paper cites Human-level control through deep reinforcement learning.nature, 518(7540):529– 533, 2015.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge Human-level control through deep reinforcement learning.nature, 518(7540):529– 533, 2015

Reference 101

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:20:31.531742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers