Paper Citation Record · LEDGER

TokenPacker: Efficient Visual Projector for Multimodal LLM

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 43 inbound Pith citation observations for arXiv:2407.02392.

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

pith.paper-citation-record.v1
2407.02392 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 43 of 43 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:55:03.126780Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T10:15:44.617819Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 5ecbc9d4-5d8e-43c3-a3a6-0753f84636a3 · inbound

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step cites this paper.

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:35:25.953654Z

Source-reported events for the cited work

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

Observation b9df33b0-369c-4531-afcb-3e94984d212a · inbound

FoPru: Focal Pruning for Efficient Large Vision-Language Models cites this paper.

FoPru: Focal Pruning for Efficient Large Vision-Language Models TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T15:31:59.552458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a986b0-1320-418f-be09-e018279d5e4d · inbound

freePruner: A Training-free Approach for Large Multimodal Model Acceleration cites this paper.

freePruner: A Training-free Approach for Large Multimodal Model Acceleration TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T14:22:07.386710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f87dbc8-cfd3-48d1-934e-08ca0e0c21ee · inbound

Importance-Based Token Merging for Efficient Image and Video Generation cites this paper.

Importance-Based Token Merging for Efficient Image and Video Generation TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T14:24:43.479995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5a7df4a-714f-4097-893a-1e71631a0529 · inbound

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings cites this paper.

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T06:04:21.920297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb1ee894-a87f-497c-acc4-0e3fbf1ef691 · inbound

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction cites this paper.

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T05:21:10.833574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 715ec7c7-15a8-4847-9b3e-4a3cdc18d2b3 · inbound

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs cites this paper.

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T00:57:32.455630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64483dff-5527-4c2b-ba48-8dfb8a2a7b10 · inbound

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression cites this paper.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.306619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0873528-fedb-49f4-88f7-8c9689af5dca · inbound

DocVLM: Make Your VLM an Efficient Reader cites this paper.

DocVLM: Make Your VLM an Efficient Reader TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T17:42:14.772001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e7046c-d4fb-4a3a-b6fb-0d8f77c9a4cd · inbound

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer cites this paper.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.286584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb05bf86-a2c6-460a-8300-fb344eaa035b · inbound

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer cites this paper.

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T12:46:59.651832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d591470-788b-498c-9f25-6218ac1d9be2 · inbound

ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming cites this paper.

ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T23:39:18.105337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726c841c-55fc-46e1-8a32-8eb056635bd1 · inbound

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM cites this paper.

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T22:52:30.221093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71909ff6-8976-435a-8fde-f3e3fed2aac0 · inbound

Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends cites this paper.

Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T22:17:27.769861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 996775d2-0132-4d8e-9dc0-582210f9d4f1 · inbound

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs cites this paper.

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T10:55:03.126780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b7a0790-66f6-455b-a4f4-4dedf1e16902 · 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 TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:15.856988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57cb93c-d8e1-4482-b0b8-4d92a2d3f68b · inbound

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference cites this paper.

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:41.755234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad7117d-d750-496d-bf95-cb4432bb11c7 · inbound

PixelThink: Towards Efficient Chain-of-Pixel Reasoning cites this paper.

PixelThink: Towards Efficient Chain-of-Pixel Reasoning TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T12:45:47.521580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5a24b9-6c20-4983-ad8f-d9e2bcdde671 · inbound

EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models cites this paper.

EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:09:04.930789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81818563-8738-439b-a096-f401ce88c5b9 · inbound

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding cites this paper.

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:56:05.333184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1413e60-66b2-4474-8cc5-4e90d4930ee2 · inbound

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings cites this paper.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.866029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8315937-1c4c-4eed-a4d5-020faa7412bf · inbound

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? cites this paper.

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:09.538863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adaa931-5207-495e-bbd1-7f0ca55cb3db · inbound

HSENet: Hybrid Spatial Encoding Network for 3D Medical Vision-Language Understanding cites this paper.

HSENet: Hybrid Spatial Encoding Network for 3D Medical Vision-Language Understanding TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:47:07.697677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c62664f3-9f31-4c76-a0de-2a28e1bfcca7 · inbound

Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs cites this paper.

Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T04:08:46.824918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4294a87b-37ca-4dd7-8684-3793d217ceef · inbound

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models cites this paper.

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:48:30.416053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede358af-656a-4c9c-a204-21158acab1c5 · inbound

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond cites this paper.

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 118

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:25.023913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c934db64-3e50-42a6-b795-2596f8f744e4 · inbound

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models cites this paper.

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T20:38:29.543299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb2fa175-544f-4b44-8abd-a3127afaa569 · inbound

FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval cites this paper.

FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:00.242206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c424190-ddff-486c-a6ef-16aaf8b4e4ef · inbound

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding cites this paper.

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:03:01.298449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3243f840-cfe4-4a19-8f2d-3f79e8bfccb5 · inbound

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs cites this paper.

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T17:38:16.589632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e74dd7-8293-4ec6-9204-f21aaa904a8f · inbound

HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation cites this paper.

HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:43:51.265156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b04a3492-ffc0-4989-92c4-271b99e7bb8a · inbound

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces cites this paper.

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T12:31:26.074772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a3c9763-f343-4d6b-95d7-997527b62566 · 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 TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:51:15.952781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9edf9c59-0678-425a-9243-243392fd084d · inbound

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification cites this paper.

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T14:42:32.675460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b131883-97a4-4f14-97af-e2abeb8c3d79 · inbound

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors cites this paper.

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:05:54.422800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d937da5-6184-48f7-91e4-6eaf389f73b2 · inbound

SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation cites this paper.

SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-18T00:25:33.013951Z

Source-reported events for the cited work

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

Observation 730fc652-2479-4f49-9878-86f56d5b5466 · inbound

UIPress: Bringing Optical Token Compression to UI-to-Code Generation cites this paper.

UIPress: Bringing Optical Token Compression to UI-to-Code Generation TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:00:59.210581Z

Source-reported events for the cited work

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

Observation de47aec6-9bef-40d4-9786-bfe0e2b88f70 · 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 TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:23:15.864498Z

Source-reported events for the cited work

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

Observation 2500fc84-b94d-418c-a669-5923dcef4800 · inbound

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

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:44.619104Z

Source-reported events for the cited work

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

Observation 8f953d7f-c32b-4170-910c-9dc353963321 · inbound

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning cites this paper.

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-31T15:16:35.532712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029a34b8-1856-4299-8a32-a5378955ea5a · inbound

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models cites this paper.

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:46:51.568021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a842a616-3f4c-4e81-9abb-82e1759158ba · inbound

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware cites this paper.

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:02.805044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c74d0f9-56b4-442e-91c8-51e2e8a3ec73 · 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 TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.255625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.