AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs | Paper Citation Record

Observation 859e0860-1a10-44ea-97f4-4cd191c0163c · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:16.876872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0729bc2a-b115-45d9-acc8-ac2492a13ee9 · outbound

This paper cites GPT-4 Technical Report.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:16.965863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 079b0580-3e41-495c-9245-cd3bdebbd3e7 · outbound

This paper cites Pixtral 12B.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Pixtral 12B

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.009599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e11e2f29-ff11-441f-916e-ae9f96db639d · outbound

This paper cites Item response theory: What it is and how you can use the irt procedure to apply it.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Item response theory: What it is and how you can use the irt procedure to apply it

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.058484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f164e09-d6e1-49a0-936e-b035439e018c · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.127745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7927f561-cbe5-4108-927e-2b125ae26319 · outbound

This paper cites Qwen2.5-VL Technical Report.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Qwen2.5-VL Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.235028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbdff70e-2be6-4d25-9704-bddeebb5f246 · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs PaliGemma: A versatile 3B VLM for transfer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.304870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e3d10c7-ce79-499f-8a62-2560758f21e8 · outbound

This paper cites A Conceptual Introduction to Hamiltonian Monte Carlo.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs A Conceptual Introduction to Hamiltonian Monte Carlo

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.377010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7256ea90-91fe-4931-adab-9785d9e88e4d · outbound

This paper cites Item response theory.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Item response theory

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.476747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a3f6e8-ed5f-428f-ae38-e30f8c9e180a · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.593586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c8d5d8f-a9db-45a7-b901-2184cca4158c · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.736081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60714eb7-06d6-49be-8b88-0d9642f4ba7d · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:17.925783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce60de2-ff36-4248-b395-deaec309f805 · outbound

This paper cites Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.004748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53d5e796-3d5d-45fe-92d6-accde172e660 · outbound

This paper cites Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:40:27.784818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d7fa42ba-1ca5-4c80-aaa8-c3ec8efc44e9 · outbound

This paper cites https://github.com/jiutiancv/JT-VL-Chat , 2024.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs https://github.com/jiutiancv/JT-VL-Chat , 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.299995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a7b1f43-7a6b-431e-9147-1e3b5b05c94c · outbound

This paper cites NVLM: Open Frontier-Class Multimodal LLMs.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs NVLM: Open Frontier-Class Multimodal LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.424220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa5e6d45-5701-4755-b6de-8fc3dbb449fd · outbound

This paper cites Smith, Hannaneh Hajishirzi, Ross Girshick, Ali Farhadi, and Aniruddha Kembhavi.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Smith, Hannaneh Hajishirzi, Ross Girshick, Ali Farhadi, and Aniruddha Kembhavi

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.565070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41571838-bf52-4676-847b-b06030067006 · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.745834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96212fa-8499-41f4-a7f8-0867af10a55c · outbound

This paper cites Easy2hard-bench: Standardized difficulty labels for profiling llm performance and generalization.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Easy2hard-bench: Standardized difficulty labels for profiling llm performance and generalization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.905650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9320d1f5-1fce-4579-85aa-230e6bdb3984 · outbound

This paper cites Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:18.998229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e074296d-34d8-4ca8-97c5-a1dff4d401d4 · outbound

This paper cites InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.144832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51196814-becb-4580-811f-3854ec73b33e · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi-modality models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Vlmevalkit: An open-source toolkit for evaluating large multi-modality models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.265190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98834668-9201-4eae-8e30-e3bf8c7b63cb · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.367021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 305abdde-2cf4-4737-95c8-7fd3ec942c1c · outbound

This paper cites Blink: Multimodal large language models can see but not perceive.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Blink: Multimodal large language models can see but not perceive

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.464859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25bf317-5f2d-40ca-955e-33badcf75361 · outbound

This paper cites H2OVL-Mississippi Vision Language Models Technical Report.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs H2OVL-Mississippi Vision Language Models Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.557859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa7790e8-d9bc-4313-af73-73e7ae890635 · outbound

This paper cites Difficulty Controllable Generation of Reading Comprehension Questions.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Difficulty Controllable Generation of Reading Comprehension Questions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.684878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5d85e1e-a194-4f42-a0bb-7503eae4c33d · outbound

This paper cites Cmmmu: A chinese massive multi-discipline multimodal understanding benchmark.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Cmmmu: A chinese massive multi-discipline multimodal understanding benchmark

Reference 27

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:40:27.277575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 66d1d3e2-7d90-4b33-b486-4af3e58fe14e · outbound

This paper cites Example of the glicko-2 system.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Example of the glicko-2 system

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.884750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a8c5b9-0124-4481-8765-c5224935fc06 · outbound

This paper cites Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:19.937612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18be7ea-ff13-41a2-981c-a9343786aeaa · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.074750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68ae5757-6f11-422c-a62d-ccb59f4426d7 · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Efficient Multimodal Learning from Data-centric Perspective

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.145924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a4f9f4-96cc-4e33-9af1-591cddb241f5 · outbound

This paper cites CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.204272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb5378d-d934-481d-b76c-bc1ad7a36ae3 · outbound

This paper cites GPT-4o System Card.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs GPT-4o System Card

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.344855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85cb312-c88b-420a-ac44-aa7a40c2c00f · outbound

This paper cites MANTIS: Interleaved Multi-Image Instruction Tuning.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs MANTIS: Interleaved Multi-Image Instruction Tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.474830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503d17eb-a3c7-42d3-861e-26b2633339aa · outbound

This paper cites Ku, Qian Liu, and Wenhu Chen.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Ku, Qian Liu, and Wenhu Chen

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.560521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f61ed3-621c-4886-b07e-099b92ef3a73 · outbound

This paper cites Automatic educational question generation with difficulty level controls.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Automatic educational question generation with difficulty level controls

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.701466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b155af45-9c20-464f-b9ec-a9994238aa44 · outbound

This paper cites A diagram is worth a dozen images.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs A diagram is worth a dozen images

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.808317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26a03eb3-3c59-43d6-b8ef-1a0cfccaeb51 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Adam: A Method for Stochastic Optimization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:20.943836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90f0ecd7-0d61-4caa-b63c-9f5112eca615 · outbound

This paper cites Auto-Encoding Variational Bayes.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Auto-Encoding Variational Bayes

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.060758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d13fbe-517a-4dc7-968d-fb2e65c111ca · outbound

This paper cites Moondream2: A vision-language model.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Moondream2: A vision-language model

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.190757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62a52ced-8ff9-455f-9d0c-2d6e37ac6711 · outbound

This paper cites What matters when building vision- language models? Advances in Neural Information Processing Systems, 37:87874–87907, 2024.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs What matters when building vision- language models? Advances in Neural Information Processing Systems, 37:87874–87907, 2024

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.254890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c0c972b-48de-4849-a504-0cbdf2699521 · outbound

This paper cites Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:40:26.790665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea43b17b-bf85-4e6e-819d-8a48bff9a40f · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs LLaVA-OneVision: Easy Visual Task Transfer

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.421761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13917c5a-bb02-4254-bbd5-83c110a4c83f · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.495770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50813fc-6d66-46ed-98d9-610c938ae99b · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Seed-bench: Benchmarking multimodal large language models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.591907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df7fb95-3801-4a8d-83c5-60b5fff0a581 · outbound

This paper cites Reform-eval: Evaluating large vision language models via unified re-formulation of task-oriented benchmarks.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Reform-eval: Evaluating large vision language models via unified re-formulation of task-oriented benchmarks

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.684259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa363727-9181-443f-a5be-3fd6cbe7a698 · outbound

This paper cites Continuous or discrete, that is the question: A survey on large multi-modal models from the perspective of input-output space extension.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Continuous or discrete, that is the question: A survey on large multi-modal models from the perspective of input-output space extension

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.767930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 810e2824-ad71-43d2-b5fb-4cbea895bf9b · outbound

This paper cites Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.845958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c8a659-4aa0-42aa-ba8f-6b73c7f96a09 · outbound

This paper cites A survey of state of the art large vision language models: Alignment, benchmark, evaluations and challenges.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs A survey of state of the art large vision language models: Alignment, benchmark, evaluations and challenges

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.916276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2060fb34-e3cf-4ee8-b7c6-167d41a4c4c5 · outbound

This paper cites DeepSeek-V3 Technical Report.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs DeepSeek-V3 Technical Report

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:21.984280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e75d31a-f5b7-4617-aa5f-3ec23d9331f3 · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.055666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b734376c-1a68-4c36-be08-0f4910be9971 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Improved Baselines with Visual Instruction Tuning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.131773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2037cf67-c670-4b76-95c5-4406e91a5acf · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.202086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf79efd-d0cc-404b-9aad-a36ac0a2091a · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.271868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7b6a80-6563-476d-bf84-ec4f198ca983 · outbound

This paper cites POINTS: Improving Your Vision-language Model with Affordable Strategies.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs POINTS: Improving Your Vision-language Model with Affordable Strategies

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.349276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03b9e430-240a-41a5-b3ea-b30911b9beff · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Ocrbench: on the hidden mystery of ocr in large multimodal models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.430479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caf27b58-1937-4909-9ec2-6de1a6df3046 · outbound

This paper cites Applications of item response theory to practical testing problems.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Applications of item response theory to practical testing problems

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:32.347477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7ef08d00-959d-4ee2-95ec-540db9247e00 · outbound

This paper cites Mmalaya2.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Mmalaya2

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:32.112816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 297b0366-7d48-44e1-8630-d5f8542fc998 · outbound

This paper cites Deepseek- vl: Towards real-world vision-language understanding, 2024.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Deepseek- vl: Towards real-world vision-language understanding, 2024

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:31.816745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea0cfe11-27b0-466a-b325-f0517896acb3 · outbound

This paper cites Deepseek- vl: Towards real-world vision-language understanding, 2024.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Deepseek- vl: Towards real-world vision-language understanding, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:31.524040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 609752e8-c675-46bc-b10a-040ce47a9637 · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.790997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e772b1-2662-4301-b53f-c44867191a32 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.864807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66051f3d-87e3-4bc9-be8c-dd4563c51b30 · outbound

This paper cites Ovis: Structural Embedding Alignment for Multimodal Large Language Model.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Ovis: Structural Embedding Alignment for Multimodal Large Language Model

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.917151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94969d3f-a8bd-4ac6-a698-06814836e0d4 · outbound

This paper cites BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:22.995802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520597f7-df58-4bc6-a649-8e2f9dcf1183 · outbound

This paper cites Taiyi: a bilingual fine-tuned large language model for diverse biomedical tasks.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Taiyi: a bilingual fine-tuned large language model for diverse biomedical tasks

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:31.245487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d0ade989-03d2-4893-9686-1a9ad66289db · outbound

This paper cites Gpt-4v-system-card.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Gpt-4v-system-card

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:30.926145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation da47228a-1241-4eea-81b9-7a3371231ebe · outbound

This paper cites Large language models are students at various levels: Zero-shot question difficulty estimation.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Large language models are students at various levels: Zero-shot question difficulty estimation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:30.663955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 244d940c-0c30-4aca-99a0-f4a451543ee4 · outbound

This paper cites Automatic differentiation in pytorch.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Automatic differentiation in pytorch

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.257385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0892b2d4-f7cb-48cc-b7e2-ac4e0151c6cb · outbound

This paper cites Transcore-m: Multimodal foundation model for transportation research.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Transcore-m: Multimodal foundation model for transportation research

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:30.397632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b256a703-e9a1-4633-883a-ef3724999d41 · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.405782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d52ffe-f59f-4b81-baae-5b941819db4e · outbound

This paper cites Efficient Benchmarking of Language Models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Efficient Benchmarking of Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.474799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91455da6-36ac-4a4e-a460-a335005e4c24 · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs tinyBenchmarks: evaluating LLMs with fewer examples

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.551580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f84bff-13ca-43a7-8ba9-0b07af0b27ad · outbound

This paper cites qihoo360/360vl-70b: An open-source large vision-language model based on llama3-70b.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs qihoo360/360vl-70b: An open-source large vision-language model based on llama3-70b

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:30.073666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 295d6d78-4cb0-4b82-9c92-e5588ff9ede2 · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Learning transferable visual models from natural language supervision

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.645848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483bd89e-23a3-4733-a06c-d82a11abeb39 · outbound

This paper cites Probabilistic models for some intelligence and attainment tests.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Probabilistic models for some intelligence and attainment tests

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:29.811540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d47bf71d-1318-4c93-a5c0-783ff35a655a · outbound

This paper cites Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:23.941064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ef07471-8c90-4b3e-a5f4-abe0866ca726 · outbound

This paper cites an unresolved cited work.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:40:29.567216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 35fe3493-ed07-4dd7-b2ab-7eef11a78a2d · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.145551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15471aa2-dd38-4627-b45e-f1a6f99d2d4b · outbound

This paper cites tiiuae/falcon-11b-vlm: A vision-language model based on falcon- 11b.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs tiiuae/falcon-11b-vlm: A vision-language model based on falcon- 11b

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:29.325515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b7e95455-61d5-4a24-a70e-853cd13385c7 · outbound

This paper cites Evaluating Cost-Accuracy Trade-offs in Multimodal Search Relevance Judgements.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Evaluating Cost-Accuracy Trade-offs in Multimodal Search Relevance Judgements

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:40:26.299574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8d7e483c-391c-4725-994d-a8d24ac5dadc · outbound

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

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs LLaMA: Open and Efficient Foundation Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.376969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343cb7bb-915e-49a8-9ab6-0fe700ab8fd4 · outbound

This paper cites Comparing Test Sets with Item Response Theory.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Comparing Test Sets with Item Response Theory

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.455373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 486e7a53-c6a3-466e-a9d4-4b5e2ffcbfdd · outbound

This paper cites Moondream1.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Moondream1

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:29.085273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b4da071-ba41-44d2-ada8-c4d333ccc169 · outbound

This paper cites Anchor Points: Benchmarking Models with Much Fewer Examples.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Anchor Points: Benchmarking Models with Much Fewer Examples

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.611594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b942e48d-4611-4c30-b882-f65be3a79527 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.725004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2590573f-3035-4269-b202-ff079e461bb5 · outbound

This paper cites Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.777981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ba1d4ed-d1df-43e7-a8bf-19aa739846be · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Chain-of-thought prompting elicits reasoning in large language models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.833222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac17db1a-9f78-4d02-9572-ad99f23879b9 · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:24.887964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fe6123b-dd9f-4f2b-ab07-a73f2d78e955 · outbound

This paper cites Adaption-of-thought: Learning question difficulty improves large language models for reasoning.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Adaption-of-thought: Learning question difficulty improves large language models for reasoning

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:28.769525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 292c4461-a251-49bc-afa8-8774d69dfb8f · outbound

This paper cites Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.034630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2c8dcad-48dd-43e4-b100-9a4a16e77231 · outbound

This paper cites Collageprompt: A benchmark for budget- friendly visual recognition with gpt-4v.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Collageprompt: A benchmark for budget- friendly visual recognition with gpt-4v

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:28.522427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8890e8ef-0ae4-4903-85c3-f15493e5c72c · outbound

This paper cites Qwen2.5 Technical Report.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Qwen2.5 Technical Report

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.219084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5336192-b0dd-44e1-8dea-3ac387e47985 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.336819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1247fd-ca59-4c6e-8d84-ab8666766be7 · outbound

This paper cites MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.406739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa99504-6013-429a-97a8-9a2d03f49ce8 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.494783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f2e1f6-1317-4010-b328-cee0148f0e27 · outbound

This paper cites Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.686235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7b04f8e-7b3d-4e43-96a6-b8aaf36a9168 · outbound

This paper cites Efficiently measuring the cognitive ability of llms: An adaptive testing perspective.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Efficiently measuring the cognitive ability of llms: An adaptive testing perspective

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:40:28.252949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 05ed1da9-f499-4840-9920-0ff28eff1f3c · outbound

This paper cites Position: AI Evaluation Should Learn from How We Test Humans.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs Position: AI Evaluation Should Learn from How We Test Humans

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T13:40:25.866299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers