Paper Citation Record · LEDGER

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning

As of 20 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2505.12782.

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

pith.paper-citation-record.v1
2505.12782 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:31:05.255901Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact1
verified fuzzy12
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 56def660-3266-4c58-9164-0b2cd8b21c6b · outbound

This paper cites From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.737480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e579f04d-2e33-4b9b-8115-b8f22369b59d · outbound

This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug- and-Play Inference Acceleration for Large Vision-Language Models.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning An Image is Worth 1/2 Tokens After Layer 2: Plug- and-Play Inference Acceleration for Large Vision-Language Models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.723133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 638f2633-cc42-41e2-8375-3de6606efa66 · outbound

This paper cites Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.128481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 302ce6b4-a0ea-4dc1-9c60-2a96ea9ef424 · outbound

This paper cites MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.133612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb40e64-be28-4b76-99a2-56491e8a5bc0 · outbound

This paper cites Chat-Scene: Bridging 3D Scene and Large Lan- guage Models with Object Identifiers.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Chat-Scene: Bridging 3D Scene and Large Lan- guage Models with Object Identifiers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.708431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0222e24d-a6e9-4c73-9f73-2ddbd3d47931 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.148435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df2a323b-8a9f-4f91-a7f2-1b967d81d89a · outbound

This paper cites GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.152574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3defb45-a16e-4060-a2fa-c09f3c08973e · outbound

This paper cites LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.693581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba1aa080-459e-4651-9dfe-03c22bba5450 · outbound

This paper cites PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:31:05.479018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7463f6bb-1c9c-40a1-abb4-6ed749c3beee · outbound

This paper cites Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.165089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b770b20-6d97-4f69-b9c6-d5b74645adb0 · outbound

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

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.170020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4071c773-4852-4b63-947a-6245f352b2ab · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.174504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd9ad6c1-c18f-422a-84c5-510fe19d8567 · outbound

This paper cites DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.178951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d999d2-4c1e-4f58-bf4b-f38d98445c9d · outbound

This paper cites AdaViT: Adaptive Vision Transformers for Ef- ficient Image Recognition.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning AdaViT: Adaptive Vision Transformers for Ef- ficient Image Recognition

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.679111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c8f83c0-ce17-4808-9c0d-ae35edc25aad · outbound

This paper cites LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.187631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 204872f8-6abc-4d74-8419-7f6ac519380a · outbound

This paper cites Visual Instruction Tuning.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Visual Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.192332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f6ad87a-adb8-4a2f-bf28-f37fa25e739c · outbound

This paper cites SQA3D: Situated Question Answering in 3D Scenes.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning SQA3D: Situated Question Answering in 3D Scenes

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.196777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cf0d9e2-c9d4-40d9-9e6a-de648d98ec4f · outbound

This paper cites ScanQA: 3D Question Answering for Spatial Scene Understanding.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning ScanQA: 3D Question Answering for Spatial Scene Understanding

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.664103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c9221f1-66b0-4ce0-84e9-beec620f3d1e · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.206553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2133ca6-7b57-4f60-92ff-c49007c09683 · outbound

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

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.648915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d291220-caee-4549-8878-79b83702ea1d · outbound

This paper cites ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.216059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c33042b-5f41-4545-a16f-9dfe5339599a · outbound

This paper cites Scan2Cap: Context-aware Dense Captioning in RGB-D Scans.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.631965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e79c0fb3-7bf1-4068-ae3c-0317a56af95c · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.225119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90af53e-3e81-4494-849d-ec53440de956 · outbound

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

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.229575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbfc9bc-c617-4a63-a4ce-5f5167622f0b · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning MMBench: Is Your Multi-modal Model an All-around Player?

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.617033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2e4980f-f42a-4fd9-8eee-0b43c8b9dbb5 · outbound

This paper cites Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.601871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 942b5564-4a52-4882-ba91-b7bd3d85e9af · outbound

This paper cites Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.243254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 119f14b7-d3ee-40b8-bc45-1ac6565513ac · outbound

This paper cites ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.586560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 943b41ae-712a-4f4d-9507-74212e377eab · outbound

This paper cites GPT-4 Technical Report.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning GPT-4 Technical Report

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:05.570825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ae47147b-84fa-4183-9750-119855bb3d41 · outbound

This paper cites An Embodied Generalist Agent in 3D World.

AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning An Embodied Generalist Agent in 3D World

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:05.255901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.