Paper Citation Record · LEDGER

Learning Compact Vision Tokens for Efficient Large Multimodal Models

As of 15 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2506.07138.

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

pith.paper-citation-record.v1
2506.07138 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:46:07.815623Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:18:00.869557Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-14T22:18:04.010679Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy33
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 51da7a16-600f-4cdb-aa5e-df1301accd5a · outbound

This paper cites Gpt-4 technical report.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Gpt-4 technical report

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.224549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 242480fd-5e69-4532-937f-d1e28933de3d · outbound

This paper cites Mme: A comprehensive evaluation benchmark for multimodal large language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Mme: A comprehensive evaluation benchmark for multimodal large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.216143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 47b7ccb5-ecec-4232-aa66-fdd0e4a612cf · outbound

This paper cites Llavolta: Efficient multi-modal models via stage-wise visual context compression.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llavolta: Efficient multi-modal models via stage-wise visual context compression

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.207041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 801ecf1d-d2b5-4ccb-8796-7d3024829c01 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.197947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a5725ba3-bb26-4992-8729-7bca59097c77 · outbound

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

Learning Compact Vision Tokens for Efficient Large Multimodal Models Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.188962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2daf0eb1-0da0-4355-a70c-aa749f051295 · outbound

This paper cites Funnel-transformer: Filtering out sequential redundancy for efficient language processing.NeurIPS, 33:4271–4282, 2020.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Funnel-transformer: Filtering out sequential redundancy for efficient language processing.NeurIPS, 33:4271–4282, 2020

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.179814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7bd3348e-dfab-4b74-9a06-0e3d3a1b3da2 · outbound

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

Learning Compact Vision Tokens for Efficient Large Multimodal Models An image is worth 16x16 words: Transformers for image recognition at scale

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.170478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation daba7e17-70db-4bb9-bec1-7ae646e68133 · outbound

This paper cites Eva: Exploring the limits of masked visual representation learning at scale.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Eva: Exploring the limits of masked visual representation learning at scale

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.160697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d92b89d5-1e62-425e-b63f-2aa2053392e7 · outbound

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

Learning Compact Vision Tokens for Efficient Large Multimodal Models Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.151659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aca5367f-5d25-4ca1-a0fe-0fd6e65d4311 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Making the v in vqa matter: Elevating the role of image understanding in visual question answering

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.142867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d5bca0a3-8e1d-4418-af6a-33bd85c37fc3 · outbound

This paper cites Llava-uhd: an lmm perceiving any aspect ratio and high-resolution images.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llava-uhd: an lmm perceiving any aspect ratio and high-resolution images

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.133673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8e06c92b-03c3-444c-a377-47214adbdf06 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Vizwiz grand challenge: Answering visual questions from blind people

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.124924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4769ae5f-cd76-453f-bbed-d41799705769 · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, 2024.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llava-next: Improved reasoning, ocr, and world knowledge, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.115256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bfaac42d-eeec-4e09-8532-e67ba4abd52b · outbound

This paper cites Gaussian Error Linear Units (GELUs).

Learning Compact Vision Tokens for Efficient Large Multimodal Models Gaussian Error Linear Units (GELUs)

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.738326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e66b3781-7f0e-48ba-ac60-57e40cc8b359 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.104245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 950b0f9c-fc84-421f-8560-abb520e05b58 · outbound

This paper cites Phi-2: The surprising power of small language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Phi-2: The surprising power of small language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.094345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e73ff6e0-9ac9-4781-8b96-d51dee059a30 · outbound

This paper cites Tokenpacker: Efficient visual projector for multimodal llm.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Tokenpacker: Efficient visual projector for multimodal llm

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.083761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e7917c06-20eb-4107-8422-23d6d2c4e03a · outbound

This paper cites Mini-gemini: Mining the potential of multi-modality vision language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Mini-gemini: Mining the potential of multi-modality vision language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.073771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b47089e5-752d-45e9-b401-9ac7e88e70e1 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Evaluating object hallucination in large vision-language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.063681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 09630c67-f9b0-4bd9-bca4-aae99b6e66cf · outbound

This paper cites Improved baselines with visual instruction tuning.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Improved baselines with visual instruction tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.755519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5b7854e-9639-456f-b092-1c9da409e187 · outbound

This paper cites Visual instruction tuning.NeurIPS, 36:34892–34916, 2023.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Visual instruction tuning.NeurIPS, 36:34892–34916, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.758411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3230107c-e0a4-43c6-a16d-116a70d0056b · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In ECCV, pages 216–233, 2024.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Mmbench: Is your multi-modal model an all-around player? In ECCV, pages 216–233, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.039655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f77dbf56-8bcc-49c9-b43f-de9eea84a03a · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.NeurIPS, 35:2507–2521, 2022.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Learn to explain: Multimodal reasoning via thought chains for science question answering.NeurIPS, 35:2507–2521, 2022

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.029686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c35a9f06-369b-4659-9e0d-b75570a45183 · outbound

This paper cites Are sixteen heads really better than one? 32, 2019.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Are sixteen heads really better than one? 32, 2019

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.019633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a5937e6c-aeca-4516-acf9-e22563477cc9 · outbound

This paper cites Efficient transformers with dynamic token pooling.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Efficient transformers with dynamic token pooling

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:08.009085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1974f68b-547a-4176-ac2b-2e6379512855 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Learning transferable visual models from natural language supervision

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.772408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65373317-e8cd-4802-be78-97e2c620473b · outbound

This paper cites Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.775586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c900fbc-8a38-45fb-8e84-9bc63e91248f · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.985357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 34caa49b-be5c-4abe-ac0b-bb8a93e3d73a · outbound

This paper cites Inter-Instance Similarity Modeling for Contrastive Learning.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Inter-Instance Similarity Modeling for Contrastive Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.781803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9472e061-3934-41ec-b802-547a485a9f57 · outbound

This paper cites Towards vqa models that can read.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Towards vqa models that can read

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.785130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd25046-4cd4-4547-bf4a-a9afc2d8984d · outbound

This paper cites Data-efficient multi-scale fusion vision transformer.Pattern Recognition, 161:111305, 2025.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Data-efficient multi-scale fusion vision transformer.Pattern Recognition, 161:111305, 2025

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.969118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1e4993ce-e0cb-48f2-82c4-8bb6a410038d · outbound

This paper cites Gemini: a family of highly capable multimodal models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Gemini: a family of highly capable multimodal models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.959421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 39e2a535-6473-4740-b768-40ed8d323bdc · outbound

This paper cites Llama: Open and efficient foundation language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llama: Open and efficient foundation language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.949990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e5e1a986-84f4-4c31-9c98-24dd65ce52d2 · outbound

This paper cites Attention is all you need.NeurIPS, 30, 2017.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Attention is all you need.NeurIPS, 30, 2017

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:46:07.796342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aec081c-b095-4e6d-82fb-aba3f29c9209 · outbound

This paper cites Calflops: A flops and params calculate tool for neural networks in pytorch framework, 2023.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Calflops: A flops and params calculate tool for neural networks in pytorch framework, 2023

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.932441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 20d354e2-bcc9-4296-84ce-84320e6d704f · outbound

This paper cites Texthawk: Exploring efficient fine-grained perception of multimodal large language models.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Texthawk: Exploring efficient fine-grained perception of multimodal large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.921814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9f0b0680-df8c-4f28-beba-fce3e75b9e52 · outbound

This paper cites Vcc: scaling transformers to 128k tokens or more by prioritizing important tokens.NeurIPS, 36:20260–20286, 2023.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Vcc: scaling transformers to 128k tokens or more by prioritizing important tokens.NeurIPS, 36:20260–20286, 2023

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.911031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e8199289-00c0-46d1-8199-3dfd759be749 · outbound

This paper cites Tinychart: Efficient chart understanding with visual token merging and program-of-thoughts learning.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Tinychart: Efficient chart understanding with visual token merging and program-of-thoughts learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.901187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 45577e7b-f0ee-4765-8fb5-8d49e649f5e2 · outbound

This paper cites Llava-mini: Efficient image and video large multimodal models with one vision token.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Llava-mini: Efficient image and video large multimodal models with one vision token

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.889734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a8f7b169-0b02-4f72-a8ee-6909f489d59f · outbound

This paper cites Diversifying the expert knowledge for task-agnostic pruning in sparse mixture-of-experts.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Diversifying the expert knowledge for task-agnostic pruning in sparse mixture-of-experts

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.879090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a30af405-ec88-473f-a549-af8c0623ceb9 · outbound

This paper cites Treat visual tokens as text? but your mllm only needs fewer efforts to see.

Learning Compact Vision Tokens for Efficient Large Multimodal Models Treat visual tokens as text? but your mllm only needs fewer efforts to see

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:46:07.867788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation c71ed3b0-259e-4ab7-9df1-52cbaf754290 · inbound

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models cites this paper.

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models Learning Compact Vision Tokens for Efficient Large Multimodal Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:00.869557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb49eef2-ff18-401d-a49c-9f8578789311 · inbound

Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression cites this paper.

Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression Learning Compact Vision Tokens for Efficient Large Multimodal Models

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:18:04.014300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.