Paper Citation Record · LEDGER

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

As of 21 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2607.08029.

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

pith.paper-citation-record.v1
2607.08029 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T13:26:41.210163Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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 exact11
verified fuzzy4
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 46457b17-b3f5-4c31-a367-792737b18171 · outbound

This paper cites Qwen3-VL Technical Report.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Qwen3-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.564230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e20b9f0-c704-43bf-9450-8ca3804dcc56 · outbound

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

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.578693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 70fd5f1d-463f-4be0-bd47-6fbc7e29f6c5 · outbound

This paper cites QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.573119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 684bf54b-097e-46a6-8050-23d72079b673 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.575811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 105cba5b-1b32-4ce6-9d21-5e3c6e833507 · outbound

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

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.563338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation beae562c-121e-4212-9aad-6cfa07ce33df · outbound

This paper cites GPT-4o System Card.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment GPT-4o System Card

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T13:27:05.578889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 64e43bcb-ab18-4ad6-873a-6f0388fc0439 · outbound

This paper cites W., and Keutzer, K.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment W., and Keutzer, K

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T13:27:06.041079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6be50f81-19f7-4863-b3df-b68e945b12fc · outbound

This paper cites Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T13:27:05.550913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f2c1fa96-858a-4dcf-b337-ef29bfb83609 · outbound

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

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment LLaVA-OneVision: Easy Visual Task Transfer

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.576101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9127f1fe-4245-49f1-9952-7e6a7468c280 · outbound

This paper cites KOSMOS-2.5: A Multimodal Literate Model.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment KOSMOS-2.5: A Multimodal Literate Model

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.554903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 43ed596a-f085-49c7-9780-be28f894ecb6 · outbound

This paper cites OpenCompass.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment OpenCompass

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T13:27:06.044951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bcdadf9e-5da8-4647-90ac-c73a8b26f86e · outbound

This paper cites Intelligence per Watt: Measuring Intelligence Efficiency of Local AI.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T13:27:05.565871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 886b1217-5517-48df-afbb-2a653e705e81 · outbound

This paper cites PaliGemma 2: A Family of Versatile VLMs for Transfer.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment PaliGemma 2: A Family of Versatile VLMs for Transfer

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T13:27:05.581553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b0e2b32a-5d42-4fda-916b-070192322dad · outbound

This paper cites DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.561580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 721c1a7a-956f-42f5-8d2e-0c63b726a54c · outbound

This paper cites A Survey of Resource-efficient LLM and Multimodal Foundation Models.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment A Survey of Resource-efficient LLM and Multimodal Foundation Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.572840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 97839c3f-ba97-4fc9-af7c-733255614867 · outbound

This paper cites Vlmq: Efficient post-training quantization for large vision- language models via hessian augmentation.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Vlmq: Efficient post-training quantization for large vision- language models via hessian augmentation

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-10T13:27:05.582238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7b0b0011-cc95-45a8-a837-f7c06c98305a · outbound

This paper cites TinyLLaVA: A Framework of Small-scale Large Multimodal Models.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment TinyLLaVA: A Framework of Small-scale Large Multimodal Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:27:05.551431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52de01df-83e9-47be-a311-b25c42389415 · outbound

This paper cites Experimental Setup To support reproducibility, we report the generation hyperparameters used for each VLM wrapper.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Experimental Setup To support reproducibility, we report the generation hyperparameters used for each VLM wrapper

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T13:27:06.036912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3956c97d-303c-4b03-9bdc-09d1ed79af3a · outbound

This paper cites an unresolved cited work.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Unresolved cited work

Reference 19

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T13:27:06.038985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 713ec9e1-8bd3-47f0-aeb0-8dc48ca25cce · outbound

This paper cites Energy consumption generally scales with latency, and accuracy degradation under quantization varies substantially across model architectures and configuration types.

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment Energy consumption generally scales with latency, and accuracy degradation under quantization varies substantially across model architectures and configuration types

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T13:27:06.043253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.