AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment | Paper Citation Record

Observation 7ac2c22a-3db1-4391-b9e4-b2faa01fe961 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.873235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a050736-faf3-42dd-af31-04a86d07851f · outbound

This paper cites Introducing Meta Llama 3: The most capable openly available LLM to date, 2024.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Introducing Meta Llama 3: The most capable openly available LLM to date, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.878998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af90698-19e9-4c2d-b08c-d9bcc438bc60 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Gemma 2: Improving Open Language Models at a Practical Size

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.883496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33cffe53-7a20-4394-b8c2-81a4d4a040de · outbound

This paper cites GPT-4 Technical Report.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment GPT-4 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.888698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39b3ff4-9a02-45c0-aeb8-91d111890281 · outbound

This paper cites SparseGPT: Massive language models can be accurately pruned in one-shot, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment SparseGPT: Massive language models can be accurately pruned in one-shot, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.893809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 074d9850-6d45-47ac-afa7-87d5fa80a25c · outbound

This paper cites A simple and effective pruning approach for large language models, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment A simple and effective pruning approach for large language models, 2023

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.898632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad6d53fb-7e62-4ac8-b6a7-51c0daa62415 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Llm-pruner: On the structural pruning of large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.904206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e89a609-dcc2-491c-8720-5ca2b7947cae · outbound

This paper cites Fluctuation-based adaptive structured pruning for large language models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Fluctuation-based adaptive structured pruning for large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.908874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e3ff13-fe7c-44d7-8c7f-f67d75b71927 · outbound

This paper cites Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:29.913456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912d186c-7927-4131-97bc-9acd9026720a · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.016955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21254411-3deb-4f1a-897e-846df2ca4c09 · outbound

This paper cites Bignas: Scaling up neural architecture search with big single-stage models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Bignas: Scaling up neural architecture search with big single-stage models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.022979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918895aa-2039-461c-b132-04d9e7021f1a · outbound

This paper cites Attentivenas: Improving neural architecture search via attentive sampling.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Attentivenas: Improving neural architecture search via attentive sampling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.028587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ffcdd17-8bb3-4407-a790-b3f4b800c2c6 · outbound

This paper cites Alphanet: Improved training of supernets with alpha-divergence.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Alphanet: Improved training of supernets with alpha-divergence

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.033535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e77131-0bb1-4ea7-a568-fee8226a24c7 · outbound

This paper cites Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.039214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7171d6d-3dc5-4d10-b95b-6203468d0ef0 · outbound

This paper cites Once-for-All: Train One Network and Specialize it for Efficient Deployment.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Once-for-All: Train One Network and Specialize it for Efficient Deployment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.044626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99092a33-0125-4b28-b0c0-989611a220fd · outbound

This paper cites Gradient surgery for multi-task learning.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Gradient surgery for multi-task learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.050418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23df3483-031f-4980-83b1-fa4f5f06e275 · outbound

This paper cites Conflict-averse gradient descent for multi-task learning.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Conflict-averse gradient descent for multi-task learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.055502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a24467d-a2fa-4b9c-a123-16d08bb7ce07 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment LoRA: Low-Rank Adaptation of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.061058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e2a80fe-defc-43da-81d3-5dc364a2e3a8 · outbound

This paper cites Tensorrt-llm, 2024.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Tensorrt-llm, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.066109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72be604c-366d-497e-919f-3598ab8f8f73 · outbound

This paper cites MLC-LLM, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment MLC-LLM, 2023

Reference 20

Resolution: parse uncertain; no resolver link, observed 2026-08-12T19:35:30.070491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3395e26-8cd9-4141-9683-3d9f875dfe64 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Pytorch: An imperative style, high-performance deep learning library

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.074742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3468837-168b-4cd9-b4c3-f073a01e5a3e · outbound

This paper cites The theory of dynamic programming.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment The theory of dynamic programming

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.079145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f05847-ef84-494d-971d-d9e1782e620e · outbound

This paper cites Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.083461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d961584-828c-441e-afe4-097cb45c8b44 · outbound

This paper cites A Comprehensive Study of Knowledge Editing for Large Language Models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment A Comprehensive Study of Knowledge Editing for Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.087787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15244494-8c89-43df-a223-6b0d52aace79 · outbound

This paper cites Knowledge Neurons in Pretrained Transformers.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Knowledge Neurons in Pretrained Transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.092157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f2183a-70a2-4b89-90a6-1b841ee4eb84 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Transformer Feed-Forward Layers Are Key-Value Memories

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.098960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b84bdce9-a71c-469c-a51e-6176cdee0a64 · outbound

This paper cites What does bert learn about the structure of language? In ACL 2019-57th Annual Meeting of the Association for Computational Linguistics, 2019.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment What does bert learn about the structure of language? In ACL 2019-57th Annual Meeting of the Association for Computational Linguistics, 2019

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.103475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb0176d4-7c36-4e88-a59a-e045890fa948 · outbound

This paper cites Locating and editing factual associations in gpt.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Locating and editing factual associations in gpt

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.107989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef8ef89b-5b45-4bb5-a05b-30d93c0b01aa · outbound

This paper cites How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.112667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6672af4e-b6f4-4403-9c7c-661b58a03566 · outbound

This paper cites Deep residual learning for image recognition.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Deep residual learning for image recognition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.117360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c879663c-11fb-4568-bba5-ac0ec6260f3a · outbound

This paper cites Editing Large Language Models: Problems, Methods, and Opportunities.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Editing Large Language Models: Problems, Methods, and Opportunities

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.122172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a04534-4b26-4923-9e5b-cabe5f33667b · outbound

This paper cites EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.126702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392a327d-5116-4ffc-8d15-109b458dfbc8 · outbound

This paper cites The Unreasonable Ineffectiveness of the Deeper Layers.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment The Unreasonable Ineffectiveness of the Deeper Layers

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.131623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e61bbb7e-0b56-47b8-82c1-f037072c12f1 · outbound

This paper cites Flexible group-level pruning of deep neural networks for on-device machine learning.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Flexible group-level pruning of deep neural networks for on-device machine learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.709874Z

Source-reported events for the cited work

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

Observation 1d22120c-601d-4f95-9fb2-d78a6faa38a5 · outbound

This paper cites Efficient joint optimization of layer-adaptive weight pruning in deep neural networks.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Efficient joint optimization of layer-adaptive weight pruning in deep neural networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.141013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a017fc1-d8cb-4b73-a198-0bbf65be26f8 · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.145804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75dc7c37-c307-4666-87fb-a6bb8813fc63 · outbound

This paper cites Mole: Mixture of lora experts.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Mole: Mixture of lora experts

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.679009Z

Source-reported events for the cited work

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

Observation 4d0a2219-df45-403c-a336-546f01181b40 · outbound

This paper cites LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.155374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e26a20-33dc-4bd7-b0ca-8159b97d1588 · outbound

This paper cites MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.160491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4389acc7-60c2-4e0f-97e4-d38bd9f159f2 · outbound

This paper cites Stanford alpaca: An instruction-following llama model.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Stanford alpaca: An instruction-following llama model

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.662834Z

Source-reported events for the cited work

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

Observation 1ebad3c0-60a4-402e-bffb-1c94a342d1b7 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, 2023

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.645889Z

Source-reported events for the cited work

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

Observation 9c9b451a-0730-4739-8088-e61a5f3d8690 · outbound

This paper cites Language model evaluation harness (package version caaf9ab).

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Language model evaluation harness (package version caaf9ab)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.627647Z

Source-reported events for the cited work

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

Observation f4bca867-0d03-444a-9e1b-96ef646fadb3 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.610413Z

Source-reported events for the cited work

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

Observation 2fd0be4b-855b-4448-b225-18cc1d0fa9f4 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Piqa: Reasoning about physical commonsense in natural language

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.184945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c7ae752-0f65-4a87-bb5a-7d46a4e11e92 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In ACL, 2019.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Hellaswag: Can a machine really finish your sentence? In ACL, 2019

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.577408Z

Source-reported events for the cited work

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

Observation 4c388efe-3aac-439a-8f26-eed23ba10016 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.194734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5373cc0-deb0-40d6-9b78-3119eacec35c · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.199244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a44a45-7036-4352-bbdf-04874b73c224 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.203624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b33512-7f09-4ab1-a7d9-4e1cf8ab0af3 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Measuring Massive Multitask Language Understanding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.207874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7616b8-9517-4e6d-b67a-9ed25d877c74 · outbound

This paper cites Pointer sentinel mixture models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Pointer sentinel mixture models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.212614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c901e8-269b-4f7e-8d6c-dd18bd80c43f · outbound

This paper cites Aligning books and movies: Towards story-like visual explanations by watching movies and reading books.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Aligning books and movies: Towards story-like visual explanations by watching movies and reading books

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.216816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89bdc06e-e9b4-48e4-89e8-fe858dfb5870 · outbound

This paper cites Attention is all you need.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Attention is all you need

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.221053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d369cb1-5597-4b4d-84c0-08e19845b49f · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.225307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77165d89-cad7-4935-a838-451e523d9a5a · outbound

This paper cites an unresolved cited work.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.229536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f88bf95c-bf63-4ef7-9be9-96c82bc7ec7c · outbound

This paper cites Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.233705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec69dda-b3ea-4cd3-aa62-1ba83d646261 · outbound

This paper cites TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.238787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89a4e57a-69a7-4f85-8f7b-eb14d374a32f · outbound

This paper cites Scaling Laws for Neural Language Models.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Scaling Laws for Neural Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.243328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4108ab37-9d2f-4907-b9e5-871be0a33a11 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Pythia: A suite for analyzing large language models across training and scaling

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.248083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14985555-59ac-44e1-8547-bda8b4f4c931 · outbound

This paper cites GLM: General Language Model Pretraining with Autoregressive Blank Infilling.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment GLM: General Language Model Pretraining with Autoregressive Blank Infilling

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.252384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6248c978-7fbe-4e07-9a93-4dca453955fb · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment OPT: Open Pre-trained Transformer Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.257228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf18923-75a3-43ca-81b0-1690dc5eaaf0 · outbound

This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.261920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b33d280d-b0b7-4812-bf90-27c9eba21c60 · outbound

This paper cites Specializing smaller language models towards multi-step reasoning.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Specializing smaller language models towards multi-step reasoning

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.266571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b37154b-71db-43cc-a101-e69071724284 · outbound

This paper cites Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.271219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f0aae3-c47b-4802-98ec-a2ff828c0117 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Optq: Accurate quantization for generative pre-trained transformers

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.276293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02385843-c7da-4565-a2ed-347b0e363b5a · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment LLM.int8(): 8-bit matrix multiplication for transformers at scale

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.470009Z

Source-reported events for the cited work

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

Observation 7767e87b-1cd3-4e64-bcd6-8c7d2ebda0bd · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.454494Z

Source-reported events for the cited work

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

Observation 9b7f6f70-38e4-4c71-87fb-f8902d9004d2 · outbound

This paper cites GPTQ: Accurate post-training compression for generative pretrained transformers.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment GPTQ: Accurate post-training compression for generative pretrained transformers

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.439474Z

Source-reported events for the cited work

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

Observation 497a3f44-4ab2-4102-8b9b-231eb065c366 · outbound

This paper cites Spqr: A sparse-quantized representation for near-lossless llm weight compression, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Spqr: A sparse-quantized representation for near-lossless llm weight compression, 2023

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.292984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c448eb37-af1f-47f7-874c-095e0719d7e3 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.296985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8db1388-8254-44c6-9180-6c42739eeef2 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.301267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbfbca65-b0e2-4c9b-849e-7eef92a2f4d1 · outbound

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

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Efficient memory management for large language model serving with pagedattention

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.305471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c18ccb-a4a9-463f-aead-949073402a78 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models, 2023.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Llm-pruner: On the structural pruning of large language models, 2023

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.400730Z

Source-reported events for the cited work

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

Observation e6c46938-4012-4947-b6b3-73e52a18c3dd · outbound

This paper cites Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.313605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f3729f-7d3a-4baa-b28a-a2f3d84f0c51 · outbound

This paper cites Slimmable Neural Networks.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Slimmable Neural Networks

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.318165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774472ea-f6cd-4826-b023-fc7a80e3487f · outbound

This paper cites Universally slimmable networks and improved training techniques.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Universally slimmable networks and improved training techniques

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.385443Z

Source-reported events for the cited work

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

Observation 306ff83c-6aae-470e-bf53-c0e8dc670e27 · outbound

This paper cites AutoSlim: Towards One-Shot Architecture Search for Channel Numbers.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.326810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec61eaac-c47a-4463-99d2-fae350495337 · outbound

This paper cites Adabits: Neural network quantization with adaptive bit-widths.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Adabits: Neural network quantization with adaptive bit-widths

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.370401Z

Source-reported events for the cited work

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

Observation 1de285e0-fa7b-4d95-ad15-87b8462be3c1 · outbound

This paper cites Switchable Precision Neural Networks.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Switchable Precision Neural Networks

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-08-12T19:35:30.497574Z

Source-reported events for the cited work

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

Observation fc99e223-59ff-4770-8c17-212bfc2e0caa · outbound

This paper cites Any-precision deep neural networks.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Any-precision deep neural networks

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.353646Z

Source-reported events for the cited work

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

Observation 07fa6e38-2884-47e1-9a07-4cc8ab5e4d49 · outbound

This paper cites Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.344764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10100ce0-99e4-4c7e-8823-e7e87bf0f52e · outbound

This paper cites Flextron: Many-in-One Flexible Large Language Model.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Flextron: Many-in-One Flexible Large Language Model

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-12T19:35:30.349664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e446d2b3-ef50-410f-bd39-cf73787386e1 · outbound

This paper cites Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.336842Z

Source-reported events for the cited work

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

Observation 3c338bb7-ca03-4d79-b2b2-4685d57f63c6 · outbound

This paper cites Limitations.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Limitations

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.319618Z

Source-reported events for the cited work

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

Observation d12b038f-019b-408d-bb0f-53af9e068fe5 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include theoretical results.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not include theoretical results

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.303621Z

Source-reported events for the cited work

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

Observation 67efbfa6-dfea-420d-bd68-9bca4378fce2 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not include experiments

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.288060Z

Source-reported events for the cited work

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

Observation bb66ef43-b795-4d21-b61c-b70ee5fb40e7 · outbound

This paper cites Guidelines: • The answer NA means that paper does not include experiments requiring code.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that paper does not include experiments requiring code

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.272817Z

Source-reported events for the cited work

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

Observation 80b9e18c-2625-447a-a961-25721f6d8a66 · outbound

This paper cites 5.1 of our paper and also provided sufficient references.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment 5.1 of our paper and also provided sufficient references

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.257119Z

Source-reported events for the cited work

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

Observation ee4d9df4-a653-48fe-87d2-a4f5ff39be85 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not include experiments

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.242240Z

Source-reported events for the cited work

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

Observation 7f4c3ed7-2993-43e5-8c27-2281d4b193b6 · outbound

This paper cites 5.1 of our paper.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment 5.1 of our paper

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.226830Z

Source-reported events for the cited work

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

Observation d6d1ab37-1ce8-46b3-9fb7-811e0d605ea4 · outbound

This paper cites Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.210370Z

Source-reported events for the cited work

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

Observation db2c3b4d-a307-4365-a513-5752fa96d014 · outbound

This paper cites Guidelines: • The answer NA means that there is no societal impact of the work performed.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that there is no societal impact of the work performed

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.192850Z

Source-reported events for the cited work

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

Observation 1053ed95-0f29-4744-bb99-43298f9855a5 · outbound

This paper cites Guidelines: • The answer NA means that the paper poses no such risks.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper poses no such risks

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.175198Z

Source-reported events for the cited work

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

Observation 3c702b83-c509-48f1-a92a-b8fe33c1a627 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not use existing assets.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not use existing assets

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.159213Z

Source-reported events for the cited work

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

Observation c82ef08d-fa6a-4304-886c-de4e33e462af · outbound

This paper cites Guidelines: • The answer NA means that the paper does not release new assets.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not release new assets

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.143558Z

Source-reported events for the cited work

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

Observation 3729f352-9fba-40bb-89d5-9291098ffdaa · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.127838Z

Source-reported events for the cited work

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

Observation 9c54f489-23f4-41e9-b7e4-311f76b1a11e · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:35:31.110658Z

Source-reported events for the cited work

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

Coverage vector

Reference resolution

Outbound references

Pith citing papers