Paper Citation Record · LEDGER

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

As of 7 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2607.23265.

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

pith.paper-citation-record.v1
2607.23265 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T04:01:48.625937Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

36 of 36 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 44e2cbf1-01e8-4686-a792-913be99b683a · outbound

This paper cites Qwen2.5-VL Technical Report.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.498396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fdae0b6-6e02-4163-9122-2a3b1334ee2b · outbound

This paper cites Token Merging: Your ViT But Faster.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Token Merging: Your ViT But Faster

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.503555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6a29bb-70d6-4dd3-8d81-cd39c0c5e2db · outbound

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

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.507558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78c3485c-74b5-4288-82fd-120e407d87bc · outbound

This paper cites Flashvid: Efficient video large lan- guage models via training-free tree-based spatiotemporal to- ken merging.arXiv preprint arXiv:2602.08024, 2026.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Flashvid: Efficient video large lan- guage models via training-free tree-based spatiotemporal to- ken merging.arXiv preprint arXiv:2602.08024, 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.511212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53dee95a-1806-44a1-b376-81e4ce862e8f · outbound

This paper cites Video-mme: The first-ever 8 comprehensive evaluation benchmark of multi-modal llms in video analysis.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Video-mme: The first-ever 8 comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.514807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 974bb5d5-894c-4430-9d4f-4be4e26c6499 · outbound

This paper cites ToSA: Token Merging with Spatial Awareness.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation ToSA: Token Merging with Spatial Awareness

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.518353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18bebb59-76ba-4594-94a4-67a8a572192a · outbound

This paper cites GPT-4o System Card.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation GPT-4o System Card

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.522434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 328529b7-f3d2-4427-8bf9-350335e6e3f6 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation LLaVA-OneVision: Easy Visual Task Transfer

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.526036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad61f7e-cc04-463a-a242-3cbd1623810a · outbound

This paper cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.529655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f210869a-2640-4a7e-9a62-7ea7291c484c · outbound

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

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.533350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8716d82-f30e-4be0-b6f8-33615a4b0f8c · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation VideoChat: Chat-Centric Video Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.536689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c47054be-7fe5-4001-a7a0-3c1377f61fbf · outbound

This paper cites Llama-vid: An image is worth 2 tokens in large language models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Llama-vid: An image is worth 2 tokens in large language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.540425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21db5e46-752e-4f57-8a64-d2ded3633464 · outbound

This paper cites Video-llava: Learning united visual repre- sentation by alignment before projection.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Video-llava: Learning united visual repre- sentation by alignment before projection

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.544682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1ab547-1060-4554-8727-6b75540b0809 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.548091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1b8d28e-7d83-408b-a3cc-124242cba75e · outbound

This paper cites HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.552316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f319d61c-aaeb-465f-a9e5-ab11449f5ee5 · outbound

This paper cites St-llm: Large language models are effective tem- poral learners.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation St-llm: Large language models are effective tem- poral learners

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.555827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eac30308-e9d8-4b64-866c-96827b195d1f · outbound

This paper cites Quota: Query-oriented token assign- ment via cot query decouple for long video comprehension.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Quota: Query-oriented token assign- ment via cot query decouple for long video comprehension

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.559642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aaadd5e-6331-453a-a5a3-c7d534396285 · outbound

This paper cites Egoschema: A diagnostic benchmark for very long- form video language understanding.Advances in Neural In- formation Processing Systems, 36:46212–46244, 2023.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Egoschema: A diagnostic benchmark for very long- form video language understanding.Advances in Neural In- formation Processing Systems, 36:46212–46244, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.562981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e4d298-80ab-4d3f-947c-2cc9deafe599 · outbound

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

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.566302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867c1159-ffdf-499f-994e-29a705b326b0 · outbound

This paper cites Holitom: Holistic token merging for fast video large language models.arXiv preprint arXiv:2505.21334,.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Holitom: Holistic token merging for fast video large language models.arXiv preprint arXiv:2505.21334,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.569757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd2233ae-0764-4622-ba01-0bc71e99655c · outbound

This paper cites TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.573191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3200ee9a-b65a-4800-9985-973813bc3e5f · outbound

This paper cites Fastvid: Dynamic density pruning for fast video large language mod- els.arXiv preprint arXiv:2503.11187, 2025.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Fastvid: Dynamic density pruning for fast video large language mod- els.arXiv preprint arXiv:2503.11187, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.576697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d925bb5-be95-46b0-9e07-dc9989631636 · outbound

This paper cites Dycoke: Dynamic compression of tokens for fast video large language models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Dycoke: Dynamic compression of tokens for fast video large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.580079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2512aef0-09e6-40ec-a128-6c78c1d71e0d · outbound

This paper cites LOOK-M: Look-once optimization in KV cache for efficient multi- modal long-context inference.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation LOOK-M: Look-once optimization in KV cache for efficient multi- modal long-context inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.583336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81fd0740-e503-445f-a570-13e1ead2dbda · outbound

This paper cites Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.586722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3d32d06-f585-474a-ab13-67d59a8b579e · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.590655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d40669d-0f7f-4372-8775-f43c0d696663 · outbound

This paper cites Lvbench: An extreme long video understanding benchmark.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Lvbench: An extreme long video understanding benchmark

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.594179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc6474f9-9105-4521-aed5-33b16a18475c · outbound

This paper cites Longvideobench: A benchmark for long-context interleaved video-language understanding.Advances in Neural Informa- tion Processing Systems, 37:28828–28857, 2024.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Longvideobench: A benchmark for long-context interleaved video-language understanding.Advances in Neural Informa- tion Processing Systems, 37:28828–28857, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.597987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cf8eaf9-3adf-41a1-aa63-a04b8662a820 · outbound

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

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.601334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30edd1d2-1f31-40a6-a0b5-1034d98c124f · outbound

This paper cites Visionzip: Longer 9 is better but not necessary in vision language models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Visionzip: Longer 9 is better but not necessary in vision language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.605144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0b34fd-c262-4970-970d-62920d28128d · outbound

This paper cites Vflowopt: A token pruning frame- work for lmms with visual information flow-guided opti- mization.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Vflowopt: A token pruning frame- work for lmms with visual information flow-guided opti- mization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.608428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d1800be-f5b8-4c39-90f5-c747fdf34328 · outbound

This paper cites Wave-vit: Unifying wavelet and transformers for visual representation learning.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Wave-vit: Unifying wavelet and transformers for visual representation learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.611796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 558d0d5d-1581-409f-98fb-9543daec9110 · outbound

This paper cites A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.615080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5631c45a-2fe2-4b42-830b-5889dc58e5cb · outbound

This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.618509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c940e4a4-e27a-4e34-b139-3498d8d14cc3 · outbound

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

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.622068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca36352-5a8f-416b-ba86-639dfcbb76bb · outbound

This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 36

Resolution: malformed identifier; no resolver link, observed 2026-08-04T04:01:48.625937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.