SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters | Paper Citation Record

Observation 609a0388-61f5-4d4f-8bab-334ba9f061f7 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.394550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f78eda28-a31b-4362-9066-1676b007fe72 · outbound

This paper cites Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.399688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad89bf29-a54e-4554-993e-c2a38d02cae8 · outbound

This paper cites Mathqa: Towards interpretable math word problem solving with operation-based formalisms, 2019.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Mathqa: Towards interpretable math word problem solving with operation-based formalisms, 2019

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.403441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c65fb43-6d32-422b-b5f5-f7e98e5c1f8b · outbound

This paper cites Qwen Technical Report.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Qwen Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.407280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5219e199-9660-4a5e-ba13-6eda36712582 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Pythia: A suite for analyzing large language models across training and scaling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.411395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf91926-3d4f-4a60-a854-f1f9a93f7d7b · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Piqa: Reasoning about physical commonsense in natural language

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.415307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc9c7778-8471-48d6-ac99-e2e7b0a8d294 · outbound

This paper cites GPT-NeoX-20B: An Open-Source Autoregressive Language Model.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.419177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa7b9b5-d346-44e6-a89f-9ac1bcf1e561 · outbound

This paper cites Language Models are Few-Shot Learners.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Language Models are Few-Shot Learners

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.422737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33217203-abf2-4e99-9754-d8f3a24df587 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.426468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99af52a5-86ed-477c-97da-3b0ec35d1cdc · outbound

This paper cites Code alpaca: An instruction-following llama model for code generation.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Code alpaca: An instruction-following llama model for code generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.429889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8a45f6-28b3-4949-b2bd-0700b1623bde · outbound

This paper cites Learning to maximize mutual information for chain-of-thought distillation.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Learning to maximize mutual information for chain-of-thought distillation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.433149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4d976e9-10fa-47c7-b95f-0791502939b2 · outbound

This paper cites LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.436326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dda9464-5803-46e1-828d-e2c8405ddf5c · outbound

This paper cites D ialog S um: A real-life scenario dialogue summarization dataset.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters D ialog S um: A real-life scenario dialogue summarization dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.439774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca0e07c-86e1-4425-bf77-755de8711dbe · outbound

This paper cites Palm: Scaling language modeling with pathways.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Palm: Scaling language modeling with pathways

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.442950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5fd9e9-6e76-4b30-9820-56d76ac01d54 · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.445935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76976001-ca3e-4cc4-8e76-993290329eff · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.448983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 384bbdd8-c598-4cc6-8732-558b9d69691f · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Training Verifiers to Solve Math Word Problems

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.452482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55dcea1e-fcb7-4a65-85bc-ba36521e10a9 · outbound

This paper cites Free dolly: Introducing the world's first truly open instruction-tuned llm, 2023.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Free dolly: Introducing the world's first truly open instruction-tuned llm, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.456036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5144d1d7-b9ea-43d0-b3b9-ac95b4ea587f · outbound

This paper cites Mutual: A dataset for multi-turn dialogue reasoning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Mutual: A dataset for multi-turn dialogue reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.459132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f976b7-223a-4a05-98af-bec7aced9cd8 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.462157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd351f96-3ef2-4134-8c23-5cb350db3938 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.465407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2947059-ec14-420b-b640-69bc0a070c9d · outbound

This paper cites an unresolved cited work.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.468388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f04ece8a-781a-4cf6-981a-a8cf6b514c72 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Qlora: Efficient finetuning of quantized llms

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.471354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d69a650-a8bd-4bfe-bada-f1598e01d261 · outbound

This paper cites Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.474327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb8c23d-e8c0-4e2b-bae4-dbe1d46a9d9a · outbound

This paper cites Blockwise compression of transformer-based models without retraining.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Blockwise compression of transformer-based models without retraining

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.477757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d9b0a07-1127-4b4f-8b2b-b5fab7e721f3 · outbound

This paper cites The Llama 3 Herd of Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The Llama 3 Herd of Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.480714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1547bb2-eb02-4cf9-ad61-c92ecfa99937 · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.483877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9373bec1-19a2-4e7b-855b-716f523cf8a0 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.486906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d554e6de-e130-4979-a77b-ffaab0f0b5f7 · outbound

This paper cites Learn-to-share: A hardware-friendly transfer learning framework exploiting computation and parameter sharing.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Learn-to-share: A hardware-friendly transfer learning framework exploiting computation and parameter sharing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.489949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77d0b6a-ef8e-45b7-aa1e-c0768c072392 · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters A framework for few-shot language model evaluation, 07 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.492841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2a0077f-9906-4d40-a7c2-332cf89e403b · outbound

This paper cites The Unreasonable Ineffectiveness of the Deeper Layers.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The Unreasonable Ineffectiveness of the Deeper Layers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.495709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 990270c8-cd96-4223-a541-89660cfc90ba · outbound

This paper cites Textbooks Are All You Need.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Textbooks Are All You Need

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.498897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 126127a4-5cba-4546-9584-de4734c56e1e · outbound

This paper cites Compressing pre-trained language models using progressive low rank decomposition.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Compressing pre-trained language models using progressive low rank decomposition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.502449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdf172f-4dc9-4564-81cb-d56f9a209242 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Distilling the Knowledge in a Neural Network

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.505557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b740735b-53ed-46ac-8c77-911256352e1a · outbound

This paper cites Training Compute-Optimal Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Training Compute-Optimal Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.508785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24872e0f-5eed-430f-a35c-01ad60f58d30 · outbound

This paper cites Language model compression with weighted low-rank factorization.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Language model compression with weighted low-rank factorization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.512142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eae92fb-3812-48f7-b5b7-4b9ef31c70f8 · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters LoRA: Low-Rank Adaptation of Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.515423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec55e8c8-09c2-491b-bdac-9477daf7f5fe · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.518499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d397db10-374b-451a-a7ef-ff47182143d8 · outbound

This paper cites safetensors.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters safetensors

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.521757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bebc7d0-9c82-473a-8ad4-c3ac6329add6 · outbound

This paper cites Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.524776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbea67cc-d6dc-4143-8b6c-4fdf9f4d9c7c · outbound

This paper cites Mistral 7B.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Mistral 7B

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.528254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1146dde1-570b-456e-b301-574fa10fb48e · outbound

This paper cites Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-08T13:44:01.008160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d05d8b5b-34a8-4366-8d4e-c58a586a8720 · outbound

This paper cites Weld, and Luke Zettlemoyer.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Weld, and Luke Zettlemoyer

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.535267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0872bdf5-f05e-4ce2-b24d-f984a37244e5 · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.538291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df2d3abd-ca64-4747-977d-7f5f91b1e126 · outbound

This paper cites arxiv-math-instruct-50.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters arxiv-math-instruct-50

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.569680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 82fa24fe-d6f5-4e80-a3b1-bf4e25e3196a · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters SqueezeLLM: Dense-and-Sparse Quantization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.544467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dce0f8e-e1f0-4d76-84ba-eaf82b5e4aa3 · outbound

This paper cites Full Stack Optimization of Transformer Inference: a Survey.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Full Stack Optimization of Transformer Inference: a Survey

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.547913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe9f86d-16ac-4127-8751-b4fb6bcc56f5 · outbound

This paper cites Speculative decoding with big little decoder.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Speculative decoding with big little decoder

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.559923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 99319401-96ec-478c-95e5-3543a552728b · outbound

This paper cites Reformer: The Efficient Transformer.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Reformer: The Efficient Transformer

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.554454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5605fd54-6203-4d08-841f-2d13198d77bf · outbound

This paper cites o pf, Yannic Kilcher, Dimitri von R \.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters o pf, Yannic Kilcher, Dimitri von R \

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.550621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 448f8bc4-5c02-4654-a90c-a552d35cd2f8 · outbound

This paper cites LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.560727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ce2381e-10f6-46c4-8bc8-c2e94232da5f · outbound

This paper cites Losparse: Structured compression of large language models based on low-rank and sparse approximation.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Losparse: Structured compression of large language models based on low-rank and sparse approximation

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.541682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 08840d56-194c-45a0-9a03-329bef4349d9 · outbound

This paper cites The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-08T13:44:00.955687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9bbb9f5b-f553-4d78-9461-5702cce38c02 · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.570594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1aac243-d292-44e6-8a38-1538e7bab617 · outbound

This paper cites MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.574242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7c1be55-0710-45b8-8297-1609f64d69ef · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Deja vu: Contextual sparsity for efficient llms at inference time

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.532044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d63f4650-1139-4eed-848c-01ff37af7fe7 · outbound

This paper cites The flan collection: Designing data and methods for effective instruction tuning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The flan collection: Designing data and methods for effective instruction tuning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.580675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f98760-770e-4885-b5f7-eb28ddd2e9b4 · outbound

This paper cites Fineweb-edu, May 2024.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Fineweb-edu, May 2024

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.518017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 029c6bc1-782e-44a0-aa33-f43bad5966ed · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Llm-pruner: On the structural pruning of large language models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.587134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4357665d-8a38-4c5f-ac05-eba6b630ff83 · outbound

This paper cites Peft: State-of-the-art parameter-efficient fine-tuning methods.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Peft: State-of-the-art parameter-efficient fine-tuning methods

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.590146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1b78aea-63f9-44a5-ac99-833b591b03f4 · outbound

This paper cites ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.593433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c46f36c-57ce-453b-8ee9-57271195c5ea · outbound

This paper cites Orca: Progressive Learning from Complex Explanation Traces of GPT-4.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.598069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0e37d9-602e-4b4e-b89a-2eae112783c5 · outbound

This paper cites Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.498518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cd3188e7-a885-4cf6-adbb-99ab332cd029 · outbound

This paper cites The lambada dataset, Aug 2016.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The lambada dataset, Aug 2016

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.604742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73e2852b-3fd7-438a-bbd9-86f2ff6cf807 · outbound

This paper cites Hovy, Pamela Forner, \'A lvaro Rodrigo, Richard F.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Hovy, Pamela Forner, \'A lvaro Rodrigo, Richard F

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.482413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94a895b8-0d03-49ae-a33b-828a0dc37633 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.610889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae97c1d-32cb-4a28-bd85-2fe2b0b93c53 · outbound

This paper cites Instruction Tuning with GPT-4.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Instruction Tuning with GPT-4

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.614144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f48c874-de2e-4c5d-af16-d8b5f722c1f3 · outbound

This paper cites Efficiently scaling transformer inference.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Efficiently scaling transformer inference

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.617414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05bb520b-de63-45e1-ac97-2cefe282825b · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.620603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d118554-e8be-428f-b59f-ac40539283d7 · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.623850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc13ed9-f377-440b-89eb-7d0e1d2795b8 · outbound

This paper cites S-LoRA: Serving Thousands of Concurrent LoRA Adapters.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.627303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4429da89-7e1a-4f88-8de7-731eb9f950dc · outbound

This paper cites Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.630570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79f7021f-7e3c-4f95-ad0f-c03563279973 · outbound

This paper cites Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.467507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d0863e9f-5c08-4595-a736-0465ac3e2d42 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters A Simple and Effective Pruning Approach for Large Language Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.638205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83636a88-52f1-4891-b66d-98e554e2fb56 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.641561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa25504b-1c32-4c06-8ab1-ac8be1fea274 · outbound

This paper cites KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.645377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba86a792-cd7d-4434-8f78-c84ca18c9055 · outbound

This paper cites C ommonsense QA : A question answering challenge targeting commonsense knowledge.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters C ommonsense QA : A question answering challenge targeting commonsense knowledge

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.648906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4414b662-01c4-436b-a618-9f0b6af1aae3 · outbound

This paper cites Multi-Domain Neural Machine Translation.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Multi-Domain Neural Machine Translation

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-08-08T13:44:00.837719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6025f9a1-8fe8-4a9d-88e3-8abc8d210e5f · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Gemini: A Family of Highly Capable Multimodal Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.655703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878a148a-0bcb-4fc8-86d7-4e755cb41522 · outbound

This paper cites Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.659142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3aa82dc-5707-4ac0-a5d0-6748380455f8 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.662881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a189eff1-a16f-4fbc-9d37-3025366e41d4 · outbound

This paper cites Smith, Iz Beltagy, and Hannaneh Hajishirzi.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Smith, Iz Beltagy, and Hannaneh Hajishirzi

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.666585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6090a7a2-414f-4013-9fd5-43057ea2c880 · outbound

This paper cites Liu, and Matt Gardner.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Liu, and Matt Gardner

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.452340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 72d3a5b1-ca63-4a16-bac2-3fb80da30ac2 · outbound

This paper cites Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.672927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197c667f-0f91-4cb0-9932-05469fef679c · outbound

This paper cites Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.676353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398d67a9-e006-4337-9adf-55117488af82 · outbound

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

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.680017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006da0f2-6bb7-4c61-bd0d-254ff8a5779e · outbound

This paper cites Wizard LM : Empowering large pre-trained language models to follow complex instructions.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Wizard LM : Empowering large pre-trained language models to follow complex instructions

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.683256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a40591c7-eb13-4dae-9979-8ad86ed6550b · outbound

This paper cites Zeroquant: Efficient and affordable post-training quantization for large-scale transformers.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Zeroquant: Efficient and affordable post-training quantization for large-scale transformers

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.432369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d552fbc1-bcdd-4087-80e6-6d7e01384118 · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters TinyLlama: An Open-Source Small Language Model

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.689555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ada6c8-054c-4cf5-b556-dffa5ae0fd7f · outbound

This paper cites AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.692882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a0cda3f-0f67-4f00-b8db-30140497589f · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters OPT: Open Pre-trained Transformer Language Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.696184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788b02db-186b-4043-aaa4-f3b04a13b843 · outbound

This paper cites Adaptive-precision framework for sgd using deep q-learning.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Adaptive-precision framework for sgd using deep q-learning

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.423105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f457a825-98a0-48cd-883c-08043957a28e · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:44:01.413628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 77948001-69c7-4cd3-8931-ccdf9ca04e35 · outbound

This paper cites Lima: Less is more for alignment.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Lima: Less is more for alignment

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.705824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7fd59a-1c84-4197-b6b6-2ef9c4a72fd9 · outbound

This paper cites write newline.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters write newline

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.708804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f32fecc0-8bc8-4ca4-ab83-82106412c486 · outbound

This paper cites @esa (Ref.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters @esa (Ref

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.712425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669dfaa8-092f-47d8-970c-c4cf8d21571f · outbound

This paper cites an unresolved cited work.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Unresolved cited work

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.717308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 555edb9b-f77f-4b11-a6a6-97964e650b49 · outbound

This paper cites an unresolved cited work.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters Unresolved cited work

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.720633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers