Paper Citation Record · LEDGER

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

As of 14 August 2026, this Paper Citation Record lists 73 of 73 outbound references and 10 inbound Pith citation observations for arXiv:2412.05819.

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

pith.paper-citation-record.v1
2412.05819 v1

Coverage vector

measured 73 of 73 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:23:18.738520Z

measured 83 of 83 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:57:32.530971Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T19:48:11.386460Z

Reference resolution

73 of 73 outbound references displayed

verified exact1
verified fuzzy26
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation af9cca93-691e-416b-aece-26acfe1cacb9 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.356250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc3c0b1-7af7-40d9-9745-df66af626c35 · outbound

This paper cites Multimodal large language models in health care: Applications, challenges, and future outlook.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Multimodal large language models in health care: Applications, challenges, and future outlook

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.704931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8b1831cd-5dcf-436b-9ffe-2064b2d15e2b · outbound

This paper cites Qwen Technical Report.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.365056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977e4197-4e10-4757-80a4-3048724a4db1 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.369183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755f1968-0778-46cb-a56c-2023e2213c83 · outbound

This paper cites Introducing our multimodal models, 2023.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Introducing our multimodal models, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.694317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aaca4f51-1d4d-4002-8de8-9af90ae780e4 · outbound

This paper cites Token Merging: Your ViT But Faster.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Token Merging: Your ViT But Faster

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.376596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2279f39-cdca-4968-bd6a-6f88994610fa · outbound

This paper cites ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.380176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd24611f-5d71-47f2-b737-b7ba2b7a7ac1 · outbound

This paper cites Show, observe and tell: Attribute-driven attention model for image captioning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Show, observe and tell: Attribute-driven attention model for image captioning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.682555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d50f9d2c-8fc1-4c9b-bad4-d1a90f425e0c · outbound

This paper cites Imram: Iterative matching with recur- rent attention memory for cross-modal image-text retrieval.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Imram: Iterative matching with recur- rent attention memory for cross-modal image-text retrieval

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.670506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a1f51f80-4cd2-4477-b5aa-eaf8a52d8ad6 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.491097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db7cf982-5136-4bdd-8a21-7b8c849cdcf1 · outbound

This paper cites MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.494894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d066c14d-e3fa-479b-9329-c87cb9a403b4 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.498892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 181bc5c6-cede-4180-a16c-967a7f8e7cf5 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.502572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f97ebf50-acbf-4769-baee-01799f66bb91 · outbound

This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.506754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c115939-9158-4eea-8c30-386cea8a6f76 · outbound

This paper cites Pearson correlation coefficient.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Pearson correlation coefficient

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.649869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 628f96cd-d9e8-4ba3-8396-e15707789759 · outbound

This paper cites A survey on multimodal large lan- guage models for autonomous driving.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs A survey on multimodal large lan- guage models for autonomous driving

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.638745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ee1115bc-874c-401e-891a-d828a6b126d5 · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.518220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082a0047-1d8e-4ef8-babc-301cd1ce799f · outbound

This paper cites HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.522486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0234ad18-c79d-43ed-8c49-05159676214b · outbound

This paper cites Explor- ing structured semantic prior for multi label recognition with incomplete labels.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Explor- ing structured semantic prior for multi label recognition with incomplete labels

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.626557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4685981f-1e81-4143-861e-703334cb700e · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.530205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd472030-80f4-47e9-9dda-2415f5a30f8b · outbound

This paper cites PaLM-E: An Embodied Multimodal Language Model.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs PaLM-E: An Embodied Multimodal Language Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.533914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac042213-1efa-4ed4-b1d5-dcae4239769a · outbound

This paper cites The Llama 3 Herd of Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs The Llama 3 Herd of Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.537742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3aa61ae-4231-4d93-a69f-8d6a900c5b4d · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.541725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a70487e-312a-47c5-bb4c-e18ee6319381 · outbound

This paper cites Anomalygpt: Detecting in- dustrial anomalies using large vision-language models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Anomalygpt: Detecting in- dustrial anomalies using large vision-language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.613138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5ca43d82-4d3f-4ee4-a754-c7936e043c96 · outbound

This paper cites Efficient Multimodal Learning from Data-centric Perspective.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Efficient Multimodal Learning from Data-centric Perspective

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.550329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 589894f9-6786-4385-a1c4-3d6dfe505f86 · outbound

This paper cites MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.554361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c4ac31-27be-42db-a67b-6f948b24ce9a · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.600304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1061a524-6356-4223-ac99-80a8a9316454 · outbound

This paper cites Introducing idefics: An open reproduction of state-of-the-art visual language model.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Introducing idefics: An open reproduction of state-of-the-art visual language model

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.587856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 46b589e5-bec0-4a3d-bf5f-75d3dd71c1b6 · outbound

This paper cites Phi-2: The surprising power of small language models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Phi-2: The surprising power of small language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.576132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e259e76a-c326-4baf-8d8c-cce36f5f320c · outbound

This paper cites Seed-bench: Bench- marking multimodal large language models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Seed-bench: Bench- marking multimodal large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.564150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 970a86f2-3855-4ca7-af90-422022a341a3 · outbound

This paper cites Llava-med: Training a large language- and-vision assistant for biomedicine in one day.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Llava-med: Training a large language- and-vision assistant for biomedicine in one day

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.551757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 31aff3c2-f15a-489a-b608-26a52167a965 · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.573814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa2c15f-b5a3-4d35-9ecb-a1318814a07b · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Evaluating Object Hallucination in Large Vision-Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.577569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e5d65b-674f-469c-b890-4ebdf1513676 · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.581794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506f0483-8b85-402b-8cbf-aa427a9dc19e · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.586120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5916b2a0-6577-4a96-bbd8-10eca8e57e71 · outbound

This paper cites MoE-LLaVA: Mixture of Experts for Large Vision-Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.590375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866ee1f5-fce6-4aad-8900-51efb24b6527 · outbound

This paper cites Microsoft coco: Common objects in context.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Microsoft coco: Common objects in context

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.594414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 106e35d1-3e28-49cb-a613-9b7eeb4fb0bc · outbound

This paper cites Improved baselines with visual instruction tuning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Improved baselines with visual instruction tuning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.532914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 63c86595-7beb-41fc-8714-8c5862dd76cc · outbound

This paper cites Visual instruction tuning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Visual instruction tuning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.521307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 46d60ad2-f810-4a4f-8652-873b21524d2e · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MMBench: Is Your Multi-modal Model an All-around Player?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.606338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e792b842-d7cc-47c0-8aee-2433f36c1769 · outbound

This paper cites Least squares quantization in pcm.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Least squares quantization in pcm

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.510328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b8e8b71c-995f-4f41-82e0-0258167937c2 · outbound

This paper cites Robollm: Robotic vision tasks grounded on multimodal large language models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Robollm: Robotic vision tasks grounded on multimodal large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.498906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b697e2cc-3337-41b9-9c0f-d012ec4cbd5d · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.618303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b70180-7039-44b3-8fb8-d7bcb64d7eec · outbound

This paper cites Some methods for classification and anal- ysis of multivariate observations.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Some methods for classification and anal- ysis of multivariate observations

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.479962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b123146d-63d4-4d92-8c87-a48a13b683dc · outbound

This paper cites DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.626572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdec5db0-8672-4016-9cd2-ebdc0d60e3f5 · outbound

This paper cites The impact of multimodal large language models on health care’s future.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs The impact of multimodal large language models on health care’s future

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.469117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0637749e-4422-4456-9a3f-32347f4afa38 · outbound

This paper cites LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.634324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535ad5b2-2954-46c8-93b2-702b2ad801d0 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Learning transferable visual models from natural language supervi- sion

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.457193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 28a5b9f5-0173-4799-aa3e-cfad16624250 · outbound

This paper cites Designing network design spaces.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Designing network design spaces

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.642232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d6f2cc-a7f1-4e0b-87cc-1a0dcf127825 · outbound

This paper cites Spearman’s rank correlation coefficient.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Spearman’s rank correlation coefficient

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.438857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c150cfcc-ba0c-428a-bbdb-603e35be8f39 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.650470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d302b1-57fa-4005-9473-e754cfc6471d · outbound

This paper cites Towards vqa models that can read.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Towards vqa models that can read

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.428280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2aca5a95-6775-4eda-af5d-71e564924332 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Gemini: A Family of Highly Capable Multimodal Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.658305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd20365-a70f-4ce4-8f81-1ccd2ec40144 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs LLaMA: Open and Efficient Foundation Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.662035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f963ca89-69a0-452d-a544-64d57abc17ad · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.665325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation add6ff33-db20-4c88-8b2e-dc0fdba1a4c0 · outbound

This paper cites Teaching matters: Investigating the role of supervision in vision transformers.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Teaching matters: Investigating the role of supervision in vision transformers

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.418620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 975e5536-81a4-4778-a559-4a3bfa2652df · outbound

This paper cites Hierarchi- cal prompt learning using clip for multi-label classification with single positive labels.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Hierarchi- cal prompt learning using clip for multi-label classification with single positive labels

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.407469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3cf076f9-39f4-465f-8f30-de9f6feb38f3 · outbound

This paper cites Cait: Triple-win compression towards high accuracy, fast inference, and favorable transferability for vits.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Cait: Triple-win compression towards high accuracy, fast inference, and favorable transferability for vits

Reference 58

Resolution: verified exact; raw_fallback, observed 2026-08-11T20:23:19.019714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f9d1d74-e30a-4b10-a53c-3f52d4d93f73 · outbound

This paper cites Repvit: Revisiting mobile cnn from vit perspective.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Repvit: Revisiting mobile cnn from vit perspective

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.679260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9174ab73-291a-4aae-9be2-b27dc785481c · outbound

This paper cites YOLOv10: Real-Time End-to-End Object Detection.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs YOLOv10: Real-Time End-to-End Object Detection

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.683446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c27f763-85ac-4383-aa07-0b32be338146 · outbound

This paper cites Large Language Models for Robotics: Opportunities, Challenges, and Perspectives.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Large Language Models for Robotics: Opportunities, Challenges, and Perspectives

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.687251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b17676b0-df9e-4568-9076-ca336662f59a · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs CogVLM: Visual Expert for Pretrained Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.691345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab0c678a-7cf2-491e-b9b1-8dc5e47dff05 · outbound

This paper cites Drivemlm: Aligning multi-modal large language models with behavioral planning states for au- tonomous driving.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Drivemlm: Aligning multi-modal large language models with behavioral planning states for au- tonomous driving

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.695485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b716bc-0e36-48b4-9771-2b3c199b3e7b · outbound

This paper cites A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.699407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39613f6b-db26-414f-8f4a-bf6c37f746f7 · outbound

This paper cites Drivegpt4: Interpretable end-to-end autonomous driving via large language model.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Drivegpt4: Interpretable end-to-end autonomous driving via large language model

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.705098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984286a4-b366-405e-97c6-53abeeab1c45 · outbound

This paper cites DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.709285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bcebf37-bfbd-47d8-be5d-00105a08efd5 · outbound

This paper cites VoCo-LLaMA: Towards Vision Compression with Large Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs VoCo-LLaMA: Towards Vision Compression with Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.713337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94685f31-4229-4530-9ccc-b34e367696c1 · outbound

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

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.717641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b20cd8-00d5-4aaf-92ac-9380db2105b9 · outbound

This paper cites TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.721571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306ad005-f887-40c6-9df7-590f6111247a · outbound

This paper cites Object recognition as next token prediction.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Object recognition as next token prediction

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.383263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b245ff0a-2cbe-4362-9aa4-30e236ab5991 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.729654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b9e68a6-f9f5-4d1c-b5c0-98c06c15dbdb · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T20:23:18.733345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93971e6d-2a07-44de-a0b5-a99af9012878 · outbound

This paper cites Llava-phi: Efficient multi-modal as- sistant with small language model, 2024.

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs Llava-phi: Efficient multi-modal as- sistant with small language model, 2024

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:23:19.365120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation cad0e01f-f301-4383-a6e4-48966203a249 · inbound

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs cites this paper.

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T00:57:32.530971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927d1f5a-eb39-4d25-a0d6-5dd9d7e7c996 · inbound

B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens cites this paper.

B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T16:38:23.330686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0684c49d-fb94-46a0-b763-5b078f39c65b · inbound

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models cites this paper.

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:08:09.626063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f56709-6ad3-47d4-80cb-9719785e5851 · inbound

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs cites this paper.

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T22:24:32.847260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf08dcb9-4566-433e-b52b-f72d9f749cab · inbound

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding cites this paper.

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T18:03:03.503424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0453dc7a-29bb-4b04-bbfe-a7ce4230f910 · inbound

Training-free Token Reduction for Vision Mamba cites this paper.

Training-free Token Reduction for Vision Mamba [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T16:16:49.428490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9cfad62-f673-4087-bdbf-bcec45303e3c · inbound

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models cites this paper.

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T13:18:04.956498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e058a539-f6ac-4009-9e94-a32b58190d49 · inbound

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs cites this paper.

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.388264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d5a48be8-1ce3-429a-aea9-64a04bc5560f · inbound

Geometry-Guided 3D Visual Token Pruning for Video-Language Models cites this paper.

Geometry-Guided 3D Visual Token Pruning for Video-Language Models [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:51:09.962866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e0112050-4ed6-437b-a8bc-307ebd8fa627 · inbound

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs cites this paper.

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T00:44:48.407469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.