Paper Citation Record · LEDGER

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models

As of 8 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2607.10640.

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

pith.paper-citation-record.v1
2607.10640 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:15:25.924075Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a4f0e9dd-c8d3-4017-965b-9c8c47d395a1 · outbound

This paper cites an unresolved cited work.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.430689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c405bd5-2a18-4324-a5e4-e0aa2dfaa8e7 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Evaluating Object Hallucination in Large Vision-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.266984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 272a5425-5446-443f-aed5-e9bcda3625cb · outbound

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

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.614205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14642a1-d05a-4c87-b185-aa573bcd257c · outbound

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

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.986010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f50efab-5fd9-46a0-8cee-eeeba7b76617 · outbound

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

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.071270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffbf409-36d6-4060-8769-4c3609b07fc6 · outbound

This paper cites Additional Theoretical Details A.1.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Additional Theoretical Details A.1

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.314515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd418c8-7ef5-47d9-ae7f-218d54fb3bc0 · outbound

This paper cites A.3 Dirichlet view under symmetrized affinity (proof of Prop.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models A.3 Dirichlet view under symmetrized affinity (proof of Prop

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.543960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2860d1e6-0719-493e-9406-07571996481e · outbound

This paper cites Finally, sinceW ⊤ = (D−1S)⊤ =SD −1, we obtain (I−αW ⊤)e= (1−α)e (0), which matches the fixed-point equation.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Finally, sinceW ⊤ = (D−1S)⊤ =SD −1, we obtain (I−αW ⊤)e= (1−α)e (0), which matches the fixed-point equation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.650913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7fa7bf-4e4b-42e3-b9cd-1fa42dcc1287 · outbound

This paper cites descendingM(c).

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models descendingM(c)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.791961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d50bb89d-00e0-4ad8-a1d0-b1c13de3e1d1 · outbound

This paper cites Beyond the raw images, the dataset provides object-level information such as locations and attributes.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Beyond the raw images, the dataset provides object-level information such as locations and attributes

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.924075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48b55ba3-b50a-4e1b-a33d-931ad5aaf9c6 · outbound

This paper cites Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Reference 416

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.837377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f04a61-2c8c-4a3b-94df-7c053bfcaee5 · outbound

This paper cites VideoPoet: A Large Language Model for Zero-Shot Video Generation.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models VideoPoet: A Large Language Model for Zero-Shot Video Generation

Reference 1998

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.131370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1394960-af2e-4697-aa7e-4a62d598d2ac · outbound

This paper cites Don’t just chase” highlighted tokens” in mllms: Revisiting visual holistic context reten- tion.arXiv preprint arXiv:2510.02912,.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Don’t just chase” highlighted tokens” in mllms: Revisiting visual holistic context reten- tion.arXiv preprint arXiv:2510.02912,

Reference 2003

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:25.205263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab643c9-0063-45fa-b2d8-9f404bc4fc4b · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:23.647752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4a8472-00a5-4f0c-b5fc-96a145d2803e · outbound

This paper cites Token Merging: Your ViT But Faster.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Token Merging: Your ViT But Faster

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:23.561997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12c8eeb-b76f-40b3-bfee-6d097cd6bed8 · outbound

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

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:23.877211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ac3e9b5-508e-4552-9943-4676ecf7f351 · outbound

This paper cites Visual question answering: from early developments to recent advances -- a survey.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Visual question answering: from early developments to recent advances -- a survey

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.018721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d492d24c-f569-4269-8ef9-0448ed942ced · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:23.756635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e140a025-f6ab-44c8-9f4b-3af7c0a71e9d · outbound

This paper cites Mini-gemini: Mining the potential of multi-modality vision language models.IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2025a.

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Mini-gemini: Mining the potential of multi-modality vision language models.IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2025a

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:24.435185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e33660-757c-41b3-9579-40658306c505 · outbound

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

Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T07:15:23.380009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.