Paper Citation Record · LEDGER

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 7 inbound Pith citation observations for arXiv:2504.17447.

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

pith.paper-citation-record.v1
2504.17447 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:43:17.664668Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:57:42.167776Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T16:09:57.135194Z

Reference resolution

46 of 46 outbound references displayed

verified exact0
verified fuzzy14
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1ada4143-35d9-45db-94cb-e14e07ef3683 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.451471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f89af446-a8ea-472b-903a-6491e0a3f9c1 · outbound

This paper cites Memory Consolidation Enables Long-Context Video Understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Memory Consolidation Enables Long-Context Video Understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.457003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b633a9e-24a4-4eea-b8d9-6ed4b62d17bd · outbound

This paper cites Scene text visual question answering.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Scene text visual question answering

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.359169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e6059f84-e991-4470-9dc6-8990444182dd · outbound

This paper cites Gram: Global reasoning for multi-page vqa.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Gram: Global reasoning for multi-page vqa

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.344862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 178e8cc1-86ac-4fb2-8dca-3d66c9b14994 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.471691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce5fd533-6a47-45dd-95a7-9eeefb8dfe10 · outbound

This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.476787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c822df91-9e47-4ab0-ab21-1567456bcd32 · outbound

This paper cites InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.482676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6de5e810-6df3-4d82-b3ea-bae87cf764c5 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.487971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9e289b-df83-4efe-a58f-38d089121ef5 · outbound

This paper cites Ma-lmm: Memory-augmented large multimodal model for long-term video understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Ma-lmm: Memory-augmented large multimodal model for long-term video understanding

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.331002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 20baadda-17aa-49cc-bb4e-72a54323a851 · outbound

This paper cites mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.497736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97737cd-0f35-4ae0-80d8-acfea68998ad · outbound

This paper cites mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.502876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c9a97cb-fba8-4e27-a9d7-e688c47c9bb3 · outbound

This paper cites Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.507757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6767b8-faa8-49bf-b35d-290f5056b60a · outbound

This paper cites Scsampler: Sampling salient clips from video for efficient action recog- nition.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Scsampler: Sampling salient clips from video for efficient action recog- nition

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.316744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b86dcd42-eb52-46b0-8cce-528cb082ef19 · outbound

This paper cites Text-Conditioned Resampler For Long Form Video Understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Text-Conditioned Resampler For Long Form Video Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.518068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36dc74f4-5747-4cbc-a24f-9190fe7a50ef · outbound

This paper cites Building and better understanding vision- language models: insights and future directions., 2024.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Building and better understanding vision- language models: insights and future directions., 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.303019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 58863500-c589-487f-90ce-db3d2db49149 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LLaVA-OneVision: Easy Visual Task Transfer

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.527084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011b615d-ccd1-4494-8f3d-1ca725d6d4cb · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.532350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1217fc4-556b-436b-9b8a-84ed79f83219 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.536688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43381703-c98e-4d46-b49d-f46925d5cb91 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Vila: On pre-training for visual language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.279282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bb7b0b27-0a16-4ee6-9ad6-9cfce0a83da2 · outbound

This paper cites Visual instruction tuning.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Visual instruction tuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.546188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4759bcae-9a95-4113-ac08-8a535f435ccb · outbound

This paper cites MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.550648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402462e8-cc6e-4395-b2f9-27734b8d7c44 · outbound

This paper cites Egoschema: A diagnostic benchmark for very long- form video language understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Egoschema: A diagnostic benchmark for very long- form video language understanding

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.254615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4c7c1924-1e88-4e5e-b8fd-eb3bbd8c7894 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Docvqa: A dataset for vqa on document images

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.559536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c4baba-695d-4bbe-b9c2-6f2680e3f6f3 · outbound

This paper cites Too many frames, not all useful: Efficient strategies for long- form video qa.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Too many frames, not all useful: Efficient strategies for long- form video qa

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.564016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82fedbd9-d060-4a2a-be62-bceff9ec89ba · outbound

This paper cites Streaming Long Video Understanding with Large Language Models.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Streaming Long Video Understanding with Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.567967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1eed15c-fea4-476d-bc42-759301067f22 · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.572620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1857db82-5077-4b20-9c24-09374eac1b50 · outbound

This paper cites Slidevqa: A dataset for document visual question answering on multiple images.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Slidevqa: A dataset for document visual question answering on multiple images

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.230330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d7b5f9fb-345a-4dae-acf8-1fe0e52fb72a · outbound

This paper cites Instructdoc: A dataset for zero-shot gener- alization of visual document understanding with instructions.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Instructdoc: A dataset for zero-shot gener- alization of visual document understanding with instructions

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.214048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dfc16086-dddb-4efb-ad8e-79989b8bfdc0 · outbound

This paper cites Hi- erarchical multimodal transformers for multipage docvqa.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Hi- erarchical multimodal transformers for multipage docvqa

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.199451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1298d1a8-b6fb-4a92-8886-b831c7296f81 · outbound

This paper cites Tarsier: Recipes for Training and Evaluating Large Video Description Models.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Tarsier: Recipes for Training and Evaluating Large Video Description Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.590383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ae6ca0-c904-4f4e-ab8f-d3c7e6208b1d · outbound

This paper cites Lvbench: An extreme long video under- standing benchmark, 2024.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Lvbench: An extreme long video under- standing benchmark, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.184832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5206eac9-1b0d-441b-943d-4ca90021443f · outbound

This paper cites VideoAgent: Long-form Video Understanding with Large Language Model as Agent.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding VideoAgent: Long-form Video Understanding with Large Language Model as Agent

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.599746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83f2be9-a27a-4baf-acab-f113d7f31e9a · outbound

This paper cites VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.604526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4584ac-7149-4d2c-8a41-910b8a38eea8 · outbound

This paper cites LongVLM: Efficient Long Video Understanding via Large Language Models.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LongVLM: Efficient Long Video Understanding via Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.609201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83dd7ddf-af62-4574-84b1-80f13ceefb27 · outbound

This paper cites LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.613816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 354fad58-8c66-4189-8728-22959c02b8fa · outbound

This paper cites Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.618225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef481088-fd65-43c7-9e6e-30081001d4aa · outbound

This paper cites Next-qa: Next phase of question-answering to explaining temporal actions.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Next-qa: Next phase of question-answering to explaining temporal actions

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.170973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8c82477e-1992-47de-bbd0-7070ecd3c9bb · outbound

This paper cites PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.627836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5ac8eb-d889-43ed-a7b2-f3af9282befb · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.633250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f6d4a8-51e4-4acc-9cb6-8c8208e0830f · outbound

This paper cites Self-chained image-language model for video localization and question answering.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Self-chained image-language model for video localization and question answering

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.156588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a1c67c44-1506-41e7-bf7e-73884a4d6389 · outbound

This paper cites Frame-Voyager: Learning to Query Frames for Video Large Language Models.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Frame-Voyager: Learning to Query Frames for Video Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.642133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8254d3-2911-476a-afff-4abea8b596ce · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Sigmoid loss for language image pre-training

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.646612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8a7fa0d-12d6-43e3-bddb-2f8f684dfb1c · outbound

This paper cites Long Context Transfer from Language to Vision.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Long Context Transfer from Language to Vision

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.650992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3a52f5-c8a9-468c-855a-24bd4205849f · outbound

This paper cites Llava- next: A strong zero-shot video understanding model, 2024.

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Llava- next: A strong zero-shot video understanding model, 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.655560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 272592ad-4daa-4e37-95db-74214230670d · outbound

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

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding MLVU: Benchmarking Multi-task Long Video Understanding

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T10:43:17.660147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38d4079-ca5a-428e-a6af-ee1209482b68 · outbound

This paper cites Selection Scoring Prompt Our prompt is based on the prompt used in SeViLA [40].

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding Selection Scoring Prompt Our prompt is based on the prompt used in SeViLA [40]

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:43:18.122194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 34d43881-d5b2-4eb7-a79c-a3532b767e37 · inbound

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes cites this paper.

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T19:03:08.072560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b25ee4a3-3132-4bde-b546-d701ac7253df · inbound

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs cites this paper.

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:56.481199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9928cae8-7e0d-41b4-9ec5-2f63929189fc · inbound

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs cites this paper.

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:56:31.830293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d481f219-c623-41d4-8a26-96118247b5cb · inbound

Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling cites this paper.

Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:09:57.137169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4065af9c-3783-4808-9ff1-13758e62168b · inbound

QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding cites this paper.

QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T14:17:02.680402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d598b017-5f0a-4bc8-9264-60f35e2e2fb8 · inbound

QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding cites this paper.

QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T17:18:41.284513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 917e71ba-b271-41a7-b130-9ebdc8cb9808 · inbound

Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models cites this paper.

Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T14:57:42.167776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.