Paper Citation Record · LEDGER

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 39 inbound Pith citation observations for arXiv:2405.20985.

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

pith.paper-citation-record.v1
2405.20985 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 39 of 39 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 39 of 39 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:47:27.417308Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T16:39:57.301173Z

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 139efa7c-ec3a-43f4-b657-741794c2b013 · inbound

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

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:58:32.399310Z

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 d810dc78-8e81-4d29-ba3c-9aadfc4826e6 · inbound

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction cites this paper.

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:12:14.719985Z

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 · inbound

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model cites this paper.

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 0438530b-fe09-49ce-9cda-43a5c62b16d7 · inbound

GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts cites this paper.

GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T18:35:54.632030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae0cb8b0-25e8-4e56-a9ff-a24c72415139 · inbound

Efficient Multi-modal Large Language Models via Visual Token Grouping cites this paper.

Efficient Multi-modal Large Language Models via Visual Token Grouping DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T12:25:00.383749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617773fb-162c-4e0b-b3b1-08ff1ad0a1d2 · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T05:21:10.950068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba662bc-0477-4522-9029-b31ae0f3edb1 · inbound

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences cites this paper.

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T04:35:37.020259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 408278cd-8194-441e-a38b-e7fe1cb0525b · inbound

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey cites this paper.

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 138

Resolution: unresolved; no resolver link, observed 2026-08-11T23:54:23.816305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fdcfc80-347f-4846-9f37-4fa7749c7790 · inbound

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay cites this paper.

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T21:31:44.581931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984286a4-b366-405e-97c6-53abeeab1c45 · inbound

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs cites this paper.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.709285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01fd9de-04df-43fa-a80f-72230581fecf · inbound

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering cites this paper.

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T14:13:24.633703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38bb3028-34b6-4410-817b-fcce0b14bdd8 · inbound

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion cites this paper.

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:42:39.606920Z

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 f1bc009d-0f9d-49cf-b3c4-b52290c5536a · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T23:39:18.191811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e66886-0670-4301-9502-412e138204d1 · inbound

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph cites this paper.

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T22:20:45.869427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 369d4a1a-0c92-4c72-b617-b8716adcf56d · inbound

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers cites this paper.

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T13:38:18.870758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8a30b9-e676-481c-b2c3-9729c9a16f13 · inbound

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction cites this paper.

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T18:02:45.199090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15349772-bd33-4549-8eea-4463566cb1df · inbound

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos cites this paper.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.417308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 374a7c16-2c10-4c62-aede-8ac0844045e3 · inbound

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation cites this paper.

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T10:46:21.296558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6efc93cf-a3aa-46b9-bd69-7d6eca2597cb · inbound

Selective Structured State Space for Multispectral-fused Small Target Detection cites this paper.

Selective Structured State Space for Multispectral-fused Small Target Detection DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:33.690880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 460a044d-4ddb-431a-87f7-c0383263c933 · inbound

MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification cites this paper.

MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:49:53.341803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf40e7ab-f15a-4d44-a5d0-db683303c096 · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-06T22:24:34.531441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34b26c7e-af54-4113-a51c-b0978ddb19d5 · inbound

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs cites this paper.

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T21:19:45.139225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710f3385-21c6-4bd4-b355-9f7a54843c1a · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T18:03:03.521866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf3ec7f-6b4a-4085-a110-40881a5299fd · inbound

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

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T17:38:18.564455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77bc4401-8c03-49ac-8110-7207b35e9308 · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T13:18:05.305866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755eb3ef-c83d-46cc-b854-83e06da943dc · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T12:31:26.101813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2329731-d797-4304-98b5-da0f72ab09f4 · inbound

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models cites this paper.

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T21:31:36.658213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df90ee04-6cd9-4fb3-83bd-b921dba7fa2a · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:18:04.021759Z

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 c19ec3be-c4d6-4286-b181-ffde45c51c61 · inbound

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs cites this paper.

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.412822Z

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 4e7580aa-13f4-4d70-a71b-9a7ef1611c41 · inbound

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models cites this paper.

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:56:05.685086Z

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 b82aa009-0379-4afd-bce0-8ca57ea4691f · inbound

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning cites this paper.

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:06:09.457346Z

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 844e4f6e-4823-40a1-a518-eb41cd3a1ae4 · inbound

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs cites this paper.

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:53.241879Z

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 61894e26-eb2c-4b84-80b6-f84aa0e4fbff · inbound

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization cites this paper.

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 75

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:56:20.524251Z

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 11b4cc3e-125f-432b-95bc-bfc5029cc13d · inbound

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding cites this paper.

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T16:39:57.302618Z

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 37f9eda6-418b-408d-aca4-af5ee0172385 · inbound

Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data cites this paper.

Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T11:44:11.253507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb207b77-30e0-4010-b5a2-f83c0954cdd8 · inbound

Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs cites this paper.

Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 252

Resolution: unresolved; no resolver link, observed 2026-08-06T00:10:37.928101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51912b01-be2c-42b6-850d-082518beb5fb · 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 DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T14:33:15.022459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0d5add-b79f-46d7-8bc6-acd9d6456e87 · inbound

When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models cites this paper.

When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T11:55:37.141110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff44c456-9f22-4a7d-8893-38d52e44efd7 · inbound

Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding cites this paper.

Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T00:09:18.269408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.