Paper Citation Record · LEDGER

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

As of 18 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 30 inbound Pith citation observations for arXiv:2411.10803.

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

pith.paper-citation-record.v1
2411.10803 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:21:14.766061Z

measured 78 of 78 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 30 of 30 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:31:12.932387Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T14:09:53.785860Z

Reference resolution

48 of 48 outbound references displayed

verified exact0
verified fuzzy21
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 90864fc1-f830-4d83-8382-7eb430667e2e · outbound

This paper cites GPT-4 Technical Report.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.545749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba16e14-8183-487c-8ee0-98d720c1287d · outbound

This paper cites HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.555290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf07494-df73-4d0f-9a8e-af7dab5165dd · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.561589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec4711df-b311-4043-81cf-720c20357eac · outbound

This paper cites Vizwiz: nearly real-time answers to visual questions.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Vizwiz: nearly real-time answers to visual questions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.723701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 59ce88ca-8c8d-4533-a298-17232e8455b6 · outbound

This paper cites Token merging: Your ViT but faster.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Token merging: Your ViT but faster

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.570780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9f75e7-9399-4572-8c87-08ccdb358a52 · outbound

This paper cites Lan- guage models are few-shot learners.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Lan- guage models are few-shot learners

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.702973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63edf87f-65b1-43e9-849d-4134efc7fae6 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models, 2024.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.580130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fb69d7-221d-451a-9d70-0359b041a938 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Qlora: Efficient finetuning of quantized llms

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.584674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0fb3af-f239-4543-98bb-7e7a38d06a3c · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.589420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7e8d820-3121-4b8c-b1c1-d96c6da4c693 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.594220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7632f18-9eeb-44a2-ae4f-f5cc592fb010 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.671374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7900d443-6024-407c-a331-a9f51ed33260 · outbound

This paper cites Cogagent: A visual language model for gui agents.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Cogagent: A visual language model for gui agents

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.657777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d2aa05c7-75c4-4c84-b425-2ed6babad4e0 · outbound

This paper cites Lita: Language instructed temporal-localization assistant.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Lita: Language instructed temporal-localization assistant

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.643799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21fe686c-4fec-48f2-ba7a-fae3718c4987 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model GQA: A new dataset for real-world visual reasoning and compositional question answering

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.629262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7f008554-ad28-4410-be93-66d9c3929c91 · outbound

This paper cites Tgif-qa: Toward spatio-temporal reasoning in visual question answering.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Tgif-qa: Toward spatio-temporal reasoning in visual question answering

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.616586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 546f1cdc-6d81-4930-9172-add9e7692d8f · outbound

This paper cites Turbo: Informativity-driven acceleration plug-in for vision-language large models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Turbo: Informativity-driven acceleration plug-in for vision-language large models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.602253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5048f24a-5b5d-4765-afc9-a1772d323ab7 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.625130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e524ec4-cee8-46f3-9228-d64dad492558 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model VideoChat: Chat-Centric Video Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.629754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3acf5675-711b-4a42-8e66-45b338422fa1 · outbound

This paper cites Univs: Unified and universal video segmentation with prompts as queries.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Univs: Unified and universal video segmentation with prompts as queries

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.579094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b1b4e3f4-7f34-42dc-ab74-a7cfcff93cca · outbound

This paper cites Not all patches are what you need: Expediting vision transformers via token reorganizations.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Not all patches are what you need: Expediting vision transformers via token reorganizations

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.566882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b8202f7-6a04-4e51-bdac-b5119199b81a · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.643364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82f5b42-a0ba-4bb4-a49b-1ebea5a60523 · outbound

This paper cites Improved baselines with visual instruction tuning.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Improved baselines with visual instruction tuning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.647508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d920a1f9-03ac-4574-9bb7-3b8b9f077175 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.653288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25aa0eac-4f08-4ec1-8bb3-d2c2c31cfad5 · outbound

This paper cites Visual instruction tuning.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Visual instruction tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.660479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120106a2-2cff-4f79-9ad0-fa0feedcb873 · outbound

This paper cites World model on million-length video and language with ringattention, 2024.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model World model on million-length video and language with ringattention, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.526830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ffe86533-16a5-4952-ad35-51c99c3969bd · outbound

This paper cites Sparse-Tuning: Adapting vision transformers with efficient fine-tuning and inference.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Sparse-Tuning: Adapting vision transformers with efficient fine-tuning and inference

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.671376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2784e95-37e2-41c9-9435-c82d1d70b763 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In European Conference on Computer Vision, pages 216–233.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Mmbench: Is your multi-modal model an all-around player? In European Conference on Computer Vision, pages 216–233

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.675533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5926270f-a6de-4566-90a6-1453b9c0c142 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.679471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 109af63e-a835-47c7-a941-64aef8be0380 · outbound

This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.684308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f795fdce-73ee-491b-8a09-57add7987980 · outbound

This paper cites Language models are unsu- pervised multitask learners.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Language models are unsu- pervised multitask learners

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.688781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09c4afb1-a030-4e76-9c51-a5a55d6471c7 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Learning transferable visual models from natural language supervision

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.492666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7f523732-1f7d-4d7c-87ad-1d0807245fc1 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Direct preference optimization: Your language model is secretly a reward model

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.480330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 218ee6ca-d0cd-406d-afa8-ab4659e9c1db · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.701155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a515ffd-d675-4c9d-8312-df2957c7c3db · outbound

This paper cites Towards VQA models that can read.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Towards VQA models that can read

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.469342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d69b5c5-551f-417e-bba5-93bfb65da4d0 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Gemini: A Family of Highly Capable Multimodal Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.713492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad812a0d-efe5-44e1-9170-5edaed08b250 · outbound

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

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.717705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd8687ff-1aa5-46c4-8d04-46ad9834cf6b · outbound

This paper cites Attention is all you need.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Attention is all you need

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.722140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b8f65aa-c970-41fe-a198-dcaa65a8dfb4 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model CogVLM: Visual Expert for Pretrained Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.725897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dd05ada-3e01-4ee0-8061-a1c98917708d · outbound

This paper cites Can i trust your answer? visually grounded video question answering.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Can i trust your answer? visually grounded video question answering

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.446333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 03ac8755-664e-4e3c-add4-7f33b7f4c244 · outbound

This paper cites Video question answer- ing via gradually refined attention over appearance and mo- tion.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Video question answer- ing via gradually refined attention over appearance and mo- tion

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.431582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8cbbe51a-842f-47a5-888f-e5c9936cb268 · outbound

This paper cites Zero-shot video question answering via frozen bidirectional language models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Zero-shot video question answering via frozen bidirectional language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.417905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c966751d-677d-4b39-983b-438a783cffc4 · outbound

This paper cites DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.741696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fd9868-b180-4977-b031-44e152b3eaa3 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Tree of thoughts: Deliberate problem solving with large language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.405013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 68427e43-9baa-4705-ba2c-1513d9ef9ee4 · outbound

This paper cites Ferret-ui: Grounded mobile ui understanding with mul- timodal llms.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Ferret-ui: Grounded mobile ui understanding with mul- timodal llms

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.392706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 09742380-dbcc-4ccb-9a39-312369a06e4f · outbound

This paper cites Magic tokens: Select diverse tokens for multi-modal object re-identification.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Magic tokens: Select diverse tokens for multi-modal object re-identification

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.377959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3ac0fd5d-705d-4259-9f12-a93c0077f143 · outbound

This paper cites Llama-adapter: Efficient fine-tuning of large language models with zero- initialized attention.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model Llama-adapter: Efficient fine-tuning of large language models with zero- initialized attention

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:21:15.362341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a467bd66-ca9b-4b1a-99ec-a406103992d5 · outbound

This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.761490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c738d7b-faee-466a-92d7-1fe9f50bc749 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T19:21:14.766061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9f142b27-cac9-4666-a592-a5452ab23db9 · inbound

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models cites this paper.

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-23T00:02:17.821582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 83320cf7-427f-47a2-9850-377bd67ebdbb · inbound

Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience cites this paper.

Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 274

Resolution: unresolved; no resolver link, observed 2026-08-15T23:31:12.932387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af17887-9523-4eef-99ba-52009acf4f1a · inbound

Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning cites this paper.

Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:15.924724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba2346a-6f98-45c9-a41c-80c1c81e0659 · inbound

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models cites this paper.

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:43:02.340523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b97be4f-8fef-4016-847b-682b060c615b · inbound

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs cites this paper.

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:06:25.772527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 731567cb-7de2-446a-b222-3b662f87a2da · inbound

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs cites this paper.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.753984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 762b43ab-b672-4b1b-b4ac-cbd32c5250f7 · inbound

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models cites this paper.

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:53.668156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8c4a900-5f2d-47c0-821f-41283f54c042 · inbound

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs cites this paper.

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T22:24:29.549834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0eca418-d976-4faa-adc6-75a5568b58d2 · inbound

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models cites this paper.

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T13:18:03.452277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ddc02e1-1c64-435e-a3f3-29e50eaa25fb · inbound

Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models cites this paper.

Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T05:51:15.987225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcff0bad-9c40-47ae-9458-c26b0d523365 · inbound

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression cites this paper.

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-21T15:10:16.490773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a264c7a1-7d9c-4008-99ed-4e807bc9dd5a · inbound

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models cites this paper.

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T02:57:46.086957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04c2190-6cf4-4248-a223-772acb2fbd56 · inbound

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models cites this paper.

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:26:26.920542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9d97cbca-ed4a-4607-b337-de37b2c26d8e · inbound

POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs cites this paper.

POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:41:04.436181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e536b025-dadf-432c-896c-4eeb897aa608 · inbound

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling cites this paper.

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:01:49.121922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e35a6860-e50e-4911-b3a9-e07247782165 · inbound

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing cites this paper.

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:58:24.845055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2adc0b12-fb7d-4065-999e-67083037bda7 · inbound

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference cites this paper.

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:43:23.798277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5eaa3acb-9858-4fa4-8e60-b1bc9710040d · inbound

EarlyTom: Early Token Compression Completes Fast Video Understanding cites this paper.

EarlyTom: Early Token Compression Completes Fast Video Understanding Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:23:15.629708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7b92e2ef-7f1f-4dde-83e9-3d2bcd497210 · inbound

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding cites this paper.

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:23:15.866979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4c9a07ee-aa4e-4607-95e9-d6b945e612eb · inbound

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models cites this paper.

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-03T11:28:04.147290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 78b96a77-ebe3-4938-adc2-b267a4e911e4 · inbound

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference cites this paper.

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T14:09:53.787431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c222cc31-d96b-440e-80bd-170880e2e2bd · inbound

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs cites this paper.

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:44.621408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 13493d25-1882-4ac2-9c22-5251d778b29b · inbound

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models cites this paper.

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T05:03:26.664752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cac17e1-2c7a-41fb-9ea6-fe26463ff5d8 · inbound

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference cites this paper.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.989028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d05624f-a8bc-480b-9d30-1829bd76b99e · inbound

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models cites this paper.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.559182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56ac6f38-9978-46a6-aff6-7293d6157dac · inbound

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs cites this paper.

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T17:23:16.283827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2aee47a-d6c7-43da-bbc9-29666f38fb20 · inbound

GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models cites this paper.

GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T14:57:56.439046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8bd15c3-4ac0-4d71-9160-9ad85923ffd8 · inbound

SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models cites this paper.

SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T16:41:28.857602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b888b749-faa7-4be3-b08e-3024b0e967d0 · inbound

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin cites this paper.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.292670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f395aee9-5bdd-4512-9f45-d0f050a073f6 · inbound

RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs cites this paper.

RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T14:33:14.961340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.