Paper Citation Record · LEDGER

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

As of 8 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 10 inbound Pith citation observations for arXiv:2505.14640.

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

pith.paper-citation-record.v1
2505.14640 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:34:44.884301Z

measured 65 of 65 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:50:02.846860Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T19:07:17.426534Z

Reference resolution

55 of 55 outbound references displayed

verified exact0
verified fuzzy7
unresolved48
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6a88210c-b53b-4908-b4e2-4d404068d158 · outbound

This paper cites LVBench: An Extreme Long Video Understanding Benchmark.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation LVBench: An Extreme Long Video Understanding Benchmark

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.208786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ed969e-dfad-49c1-9133-7e0750fa635e · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.317680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7ad542-9a07-4b88-bba4-3cd40cdc2b28 · outbound

This paper cites Video Anomaly Detection and Explanation via Large Language Models.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video Anomaly Detection and Explanation via Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.477549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d5f0c6b-03c9-4506-9af8-f0464c479552 · outbound

This paper cites Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.586160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77b6f11-b337-4d0a-9a24-bfdfca92ecb7 · outbound

This paper cites Towards automatic learning of procedures from web instructional videos.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Towards automatic learning of procedures from web instructional videos

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.675590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbb17e75-ffea-475a-947c-10ab364bd87b · outbound

This paper cites Long Context Transfer from Language to Vision.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Long Context Transfer from Language to Vision

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.769437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f52197b2-3d0b-4a6e-8276-e907aa5a7935 · outbound

This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.848837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e55e230-5270-4ea2-ba9d-10a36c347294 · outbound

This paper cites VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:40.968075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a97207d3-7a08-4b04-b7be-0cd06df75772 · outbound

This paper cites InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.079838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08eef1c9-d3c6-4b8e-a355-ced9c4eaa905 · outbound

This paper cites Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.182215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 809ec41f-47d5-4412-a93c-ca8d346ecae4 · outbound

This paper cites Token-efficient long video understanding for multimodal llms.arXiv preprint arXiv:2503.04130, 2025.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Token-efficient long video understanding for multimodal llms.arXiv preprint arXiv:2503.04130, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.295575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac6fee9-ec53-406f-b2b4-f7c2e83cff95 · outbound

This paper cites BIMBA: Selective-Scan Compression for Long-Range Video Question Answering.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.423639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aece33d9-7349-46da-b737-66bdd2dbf49b · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.495843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c716fa61-58fb-4624-89ce-fe750b5d2a98 · outbound

This paper cites VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.595618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34216a65-fbda-4284-9c4c-1b6854591650 · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.669333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157d2750-e5aa-4ea4-9f87-c7e1e62a4782 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.743812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4b19fd-09e3-4e4d-95d7-a4aaf5e427f6 · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.886033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e33eeb5-d633-4f8a-b2ed-99519e4ae733 · outbound

This paper cites Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:41.992087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d257b92-d56b-4914-867c-72506d73fc7e · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation MLVU: Benchmarking Multi-task Long Video Understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.108152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f84637-01cb-4874-a219-6fbf78ea032e · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Longvideobench: A benchmark for long- context interleaved video-language understanding.Advances in Neural Information Processing Systems, 37:28828–28857, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.202827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f3d0a31-25bb-492d-a763-2c477de4a226 · outbound

This paper cites Hourvideo: 1-hour video- language understanding.Advances in Neural Information Processing Systems, 37:53168–53197, 2024.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Hourvideo: 1-hour video- language understanding.Advances in Neural Information Processing Systems, 37:53168–53197, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:46.268970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4cbf0ae1-1f36-4988-99b6-e62437f5ba40 · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.341438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f383376-799c-40e8-b0ff-10aae3869e41 · outbound

This paper cites Qwen2.5-VL Technical Report.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Qwen2.5-VL Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.438272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9b5974-c0ef-464f-93fd-7d8253ab8b18 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation VideoChat: Chat-Centric Video Understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.546538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe5c5d6-7f0e-4d57-a531-0314a6b3bbd8 · outbound

This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.650236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9db9ddf-06ec-471d-8a9e-933d2d1fbcb8 · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation MANTIS: Interleaved Multi-Image Instruction Tuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.725167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc29b80a-afa0-4295-88e0-6ee1ce4abb53 · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.813436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911ec23a-c43c-4dbf-989f-a33908344c6f · outbound

This paper cites Mvbench: A comprehensive multi-modal video understanding benchmark.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Mvbench: A comprehensive multi-modal video understanding benchmark

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.886209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce17acaf-da91-44b8-a33a-65f9f5f53e0c · outbound

This paper cites Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:42.981605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0cc6776-42c0-4274-841d-926965e00b77 · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.096309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cac2fae-867a-4ca3-81ec-80b4cd26c169 · outbound

This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.173823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5523b6de-9a63-4e83-8221-c14dd59cc6bc · outbound

This paper cites Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.251039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56cf553-118f-4410-91a7-10e529619f69 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.353762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d083842-2e43-4ed1-97ad-f4013fb07b65 · outbound

This paper cites Vript: A video is worth thousands of words.Advances in Neural Information Processing Systems, 37:57240–57261, 2024.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Vript: A video is worth thousands of words.Advances in Neural Information Processing Systems, 37:57240–57261, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.440428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 782cb605-d43c-49b8-be75-4e6046766571 · outbound

This paper cites Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.506440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 085e1bbd-1e7e-441c-bca8-6507ba764d3f · outbound

This paper cites Video question answering via gradually refined attention over appearance and motion.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video question answering via gradually refined attention over appearance and motion

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.574670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2e9a99-d3cd-4e3a-bbe4-0395d87eacb7 · outbound

This paper cites Activitynet-qa: A dataset for understanding complex web videos via question answering.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Activitynet-qa: A dataset for understanding complex web videos via question answering

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.650831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647e48b4-0e88-4c5d-82ce-b6601f34a514 · outbound

This paper cites TempCompass: Do Video LLMs Really Understand Videos?.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation TempCompass: Do Video LLMs Really Understand Videos?

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.723261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29aaa453-09ca-4625-84b3-d9457014c874 · outbound

This paper cites VideoVista: A Versatile Benchmark for Video Understanding and Reasoning.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation VideoVista: A Versatile Benchmark for Video Understanding and Reasoning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.788047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee2d8f7-c7d7-4872-8ffd-955bf72fc76f · outbound

This paper cites Measuring short-form factuality in large language models.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Measuring short-form factuality in large language models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.846476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab987bd-e7c2-4885-ba42-fd30ab5413d9 · outbound

This paper cites Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:43.911417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73cd584-1302-45ee-9b4f-ad87622b26ea · outbound

This paper cites A Survey on LLM-as-a-Judge.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation A Survey on LLM-as-a-Judge

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.002274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490bec7a-661d-4ac6-85fa-759897b69dbd · 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.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.072681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c76730be-8774-46a2-a7c2-37b02a43f9a7 · outbound

This paper cites Gpt-4o.https://openai.com/index/hello-gpt-4o/, 2024.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Gpt-4o.https://openai.com/index/hello-gpt-4o/, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:46.047734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d87df07-319c-4926-b206-0ca0809dfd24 · outbound

This paper cites Gpt-4o mini: Advancing cost-efficient intelligence, July 2024.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Gpt-4o mini: Advancing cost-efficient intelligence, July 2024

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:45.877992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d0f93d1e-fae4-425a-bff1-0880eecedd1f · outbound

This paper cites Introducing gpt-4.1 in the api, April 2025.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Introducing gpt-4.1 in the api, April 2025

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:45.790494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f669b362-f506-4ab3-97ad-60abaef86525 · outbound

This paper cites Gemini 2.5: Our most intelligent ai model, March.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Gemini 2.5: Our most intelligent ai model, March

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:45.725060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1bebcfb6-ddfd-44f2-a173-13b10dc86f4f · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.468889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d0872ad-c2e1-40e5-a047-d42e50b38f36 · outbound

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

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.518133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f50624-c532-4090-9107-576c2a735bad · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.591263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb22c9ce-78de-42ef-8966-21a2949b6f12 · outbound

This paper cites Phi-4 Technical Report.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Phi-4 Technical Report

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.670107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25113abc-91cd-44f7-93f6-2d069f44df5a · outbound

This paper cites Longllava: Scaling multi-modal llms to 1000 images efficiently via a hybrid architecture.arXiv preprint arXiv:2409.02889, 2024.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Longllava: Scaling multi-modal llms to 1000 images efficiently via a hybrid architecture.arXiv preprint arXiv:2409.02889, 2024

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.746446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16b9d63-0c2a-4bd7-8b01-f283f01c91d8 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T15:34:44.818600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff54a88f-14c1-4d97-958e-95fd6b6afaba · outbound

This paper cites Keep" if the question can be answered by someone who has watched the video, even if the answer requires reasoning or summarizing visual or auditory evidence. -.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Keep" if the question can be answered by someone who has watched the video, even if the answer requires reasoning or summarizing visual or auditory evidence. -

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:45.565691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0a5fdf07-81df-48d0-b405-ba843d7a7362 · outbound

This paper cites Accessed: 2025-05-08.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation Accessed: 2025-05-08

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:34:45.668732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation a0e8be73-74c8-40ed-ac7e-74a5cf6f213b · inbound

Vid-SME: Membership Inference Attacks against Large Video Understanding Models cites this paper.

Vid-SME: Membership Inference Attacks against Large Video Understanding Models VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:50:02.846860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7fc560d-b42f-45f3-a437-4be1ade2a1d1 · inbound

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification cites this paper.

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T23:13:11.304314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39eb555c-eb3a-4d13-b80d-f9c4fac7983e · inbound

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding cites this paper.

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-16T04:21:29.796098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 47adbc6b-9538-4066-9e0a-a2ccd64bb11c · inbound

TrajTok: Learning Trajectory Tokens enables better Video Understanding cites this paper.

TrajTok: Learning Trajectory Tokens enables better Video Understanding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:16:31.811999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 920533a0-f3fe-4684-a31e-1a4b0b8223d9 · inbound

TrajTok: Learning Trajectory Tokens enables better Video Understanding cites this paper.

TrajTok: Learning Trajectory Tokens enables better Video Understanding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T20:38:40.952686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13235850-057d-420d-b4cf-99c338778fd2 · inbound

Video-Oasis: Rethinking Evaluation of Video Understanding cites this paper.

Video-Oasis: Rethinking Evaluation of Video Understanding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T15:38:41.390945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5eeacb-ba77-4cfc-97f9-0dba3b9c2840 · inbound

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors cites this paper.

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:11:25.138117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 280e7169-00b3-4883-bce5-1fc4884e04b7 · inbound

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity cites this paper.

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-07-02T19:07:17.427951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 84ee4e48-c29d-4129-aa2e-0182b72b4e4e · inbound

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding cites this paper.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.835407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40587f60-b205-4071-bfe4-bd9aa258a220 · inbound

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model cites this paper.

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 155

Resolution: unresolved; no resolver link, observed 2026-07-31T06:20:14.256778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.