Paper Citation Record · LEDGER

Token Sequence Compression for Efficient Multimodal Computing

As of 19 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2504.17892.

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

pith.paper-citation-record.v1
2504.17892 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:34:16.703536Z

measured 26 of 26 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:31:44.517145Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-11T21:31:45.066251Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy18
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4a78ded4-8a92-4aaa-a465-8944dcc5a272 · outbound

This paper cites A multimodal architecture for ai agents, 2023.

Token Sequence Compression for Efficient Multimodal Computing A multimodal architecture for ai agents, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:17.061184Z

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 a5d2f209-181e-496d-8490-615ba2603449 · outbound

This paper cites Token merging: Your vit but faster.

Token Sequence Compression for Efficient Multimodal Computing Token merging: Your vit but faster

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:17.047608Z

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 693a7eb5-bfbe-4cb5-81e3-e487fa364f70 · outbound

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

Token Sequence Compression for Efficient Multimodal Computing An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:17.033981Z

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 c43e1943-2d31-402e-8503-8685a083bf33 · outbound

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

Token Sequence Compression for Efficient Multimodal Computing MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.616677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea89dfbb-b98e-4bb9-913a-73c111eb7851 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

Token Sequence Compression for Efficient Multimodal Computing Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:17.020084Z

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 c0443a45-2164-455c-b96d-6d119e3cdb53 · outbound

This paper cites Perceiver: General Perception with Iterative Attention.

Token Sequence Compression for Efficient Multimodal Computing Perceiver: General Perception with Iterative Attention

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.625879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3092b459-a3eb-40c7-8e2b-4c055d4cefc8 · outbound

This paper cites Towards efficient visual-language alignment of the q-former for visual reason- ing tasks.

Token Sequence Compression for Efficient Multimodal Computing Towards efficient visual-language alignment of the q-former for visual reason- ing tasks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:17.006773Z

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 769df055-957c-4c70-9a3c-61711c810f86 · outbound

This paper cites Llava-onevision: Easy visual task transfer.

Token Sequence Compression for Efficient Multimodal Computing Llava-onevision: Easy visual task transfer

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.993732Z

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 9cc093b6-24cf-42f2-8872-ac28aa6964cf · outbound

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

Token Sequence Compression for Efficient Multimodal Computing Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.980827Z

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 b6c77503-6edc-415d-b963-a5a1caea6dfb · outbound

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

Token Sequence Compression for Efficient Multimodal Computing Evaluating Object Hallucination in Large Vision-Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.642522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef17429c-fcbc-4651-a657-d8d1282c74f3 · outbound

This paper cites Vila: On pre-training for visual language models.

Token Sequence Compression for Efficient Multimodal Computing Vila: On pre-training for visual language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.967529Z

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 3d034a8a-b008-4a08-9316-0f1a5407658d · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Token Sequence Compression for Efficient Multimodal Computing Improved Baselines with Visual Instruction Tuning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.650651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b10226c-38a9-49f4-8ad8-231b41d9079d · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge.

Token Sequence Compression for Efficient Multimodal Computing Llava-next: Im- proved reasoning, ocr, and world knowledge

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.954232Z

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 50708892-7149-437b-9553-899a08765bc6 · outbound

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

Token Sequence Compression for Efficient Multimodal Computing MMBench: Is Your Multi-modal Model an All-around Player?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.659149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ade9eed7-f91b-4eab-8e3e-677dacce5f1b · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Token Sequence Compression for Efficient Multimodal Computing Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.941028Z

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 84364a5f-d43c-4bcb-95ec-5e1b3323eb15 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Token Sequence Compression for Efficient Multimodal Computing Learning transferable visual models from natural language supervision

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.927347Z

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 169b392e-d44b-4f91-a208-eb8275377bae · outbound

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

Token Sequence Compression for Efficient Multimodal Computing Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.914243Z

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 2255e0cc-cfa5-4979-9417-87a98d688b15 · outbound

This paper cites Towards vqa models that can read.

Token Sequence Compression for Efficient Multimodal Computing Towards vqa models that can read

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.900023Z

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 ed5fc4ea-c91a-443b-b807-3a5321940efe · outbound

This paper cites Next-gpt: Any-to-any multimodal llm.

Token Sequence Compression for Efficient Multimodal Computing Next-gpt: Any-to-any multimodal llm

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.885111Z

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 72e1df33-5ca7-4d9e-8236-2a4417ee3bf8 · outbound

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

Token Sequence Compression for Efficient Multimodal Computing Visionzip: Longer is better but not necessary in vision language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.871734Z

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 581969a4-9e02-4872-bedd-83577b5e6cc4 · outbound

This paper cites X-vila: Cross-modality align- ment for large language model.

Token Sequence Compression for Efficient Multimodal Computing X-vila: Cross-modality align- ment for large language model

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.858512Z

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 736433ff-84ff-4c46-b937-5ef4e7766373 · outbound

This paper cites Mm-vet: Evaluating large multimodal models for integrated capabilities.

Token Sequence Compression for Efficient Multimodal Computing Mm-vet: Evaluating large multimodal models for integrated capabilities

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.844846Z

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 1976f3d4-e1ff-4750-82be-1a0e20bd777b · outbound

This paper cites LLM Inference Unveiled: Survey and Roofline Model Insights.

Token Sequence Compression for Efficient Multimodal Computing LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.695161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 980db933-c9f3-4f20-b082-57dd7fdb5880 · outbound

This paper cites Sigmoid loss for language image pre-training.

Token Sequence Compression for Efficient Multimodal Computing Sigmoid loss for language image pre-training

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:34:16.831138Z

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 c34eabbf-2f40-45e8-8169-338c768cda8b · outbound

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

Token Sequence Compression for Efficient Multimodal Computing SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T10:34:16.703536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a809c974-a1d4-4aa0-a0aa-b8b498adb9a9 · 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 Token Sequence Compression for Efficient Multimodal Computing

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-11T21:31:45.074721Z

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.