IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs | Paper Citation Record

Observation e02ffcd6-58d6-4a15-b389-789cab693e83 · outbound

This paper cites Language models are few-shot learners.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Language models are few-shot learners

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.780473Z

Source-reported events for the cited work

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

Observation b8a991d5-6b0b-4def-930f-1a8017c5852d · outbound

This paper cites GPT-4 Technical Report.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.783088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d4aa57-f0f0-4aae-bcdc-fdc7841a407e · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LLaMA: Open and Efficient Foundation Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.787925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba488df6-c1d5-49e5-93d3-e8c434ff5840 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.792033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d914eadc-9670-4b8a-b592-a95e649f1f77 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.796435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47baf3dd-106c-437c-ab2b-4f3267a0dd2a · outbound

This paper cites Large Language Models: A Survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Large Language Models: A Survey

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.801165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93db207e-1bd1-4efe-864d-574316170933 · outbound

This paper cites A Survey of Large Language Models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs A Survey of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.805536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 198297c3-56fb-40a5-af1a-930268614b8c · outbound

This paper cites Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.809349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7051ad6-9582-4943-a991-5f1b3f762708 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.812759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff95a4aa-43fb-4058-b81f-a1875abb4bd2 · outbound

This paper cites Large language models in ﬁnance: A survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Large language models in ﬁnance: A survey

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.761879Z

Source-reported events for the cited work

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

Observation d3bd051e-56f3-4363-ae45-38c748120ad9 · outbound

This paper cites ChatGPT for good? on opportunities and challenges of large language models for education.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs ChatGPT for good? on opportunities and challenges of large language models for education

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.751309Z

Source-reported events for the cited work

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

Observation cfa1b187-2365-48ca-bbaa-c171a10ae1a8 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.823522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6405444b-f2c4-420c-adc6-54d42b3e6a9b · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.739802Z

Source-reported events for the cited work

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

Observation 62ecb2e1-2ac1-4ecc-80ae-ab648109dc97 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.830665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1fd1fcf-879b-4f4c-9811-38fcf5d07b5c · outbound

This paper cites Transformers in vision: A survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Transformers in vision: A survey

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.728417Z

Source-reported events for the cited work

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

Observation e4b91528-cec1-48c3-ba14-24d1623d5f83 · outbound

This paper cites Multimodal few-shot learning with frozen language models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Multimodal few-shot learning with frozen language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.716906Z

Source-reported events for the cited work

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

Observation 4f3b3a45-e132-4b39-a8db-1ada099ed34d · outbound

This paper cites Video understanding with large language models: A survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Video understanding with large language models: A survey

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.842227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6a75d1a-adf9-44d3-b2a1-a4922ef02ac5 · outbound

This paper cites From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.845769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0615bc-fe54-49ab-b707-6a890db5d7b0 · outbound

This paper cites A Survey on Multimodal Large Language Models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs A Survey on Multimodal Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.849625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3348bc08-d6d7-4a01-98a1-80a6b32f561f · outbound

This paper cites Vision-language models for vision tasks: A survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Vision-language models for vision tasks: A survey

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.853080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 478e8dfe-10fd-48c0-9f8b-c1fa39e5f388 · outbound

This paper cites MovieChat: From dense token to sparse memory for long video understanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs MovieChat: From dense token to sparse memory for long video understanding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.699025Z

Source-reported events for the cited work

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

Observation 628d42a5-194f-4540-a0b6-571c0dd4267c · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs MA-LMM: Memory-augmented large multimodal model for long-term video understanding

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.688677Z

Source-reported events for the cited work

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

Observation 7ca2d4c2-f622-4168-b330-c8e425bf9916 · outbound

This paper cites Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.863339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb5cceb3-9cb7-4f50-919a-1636faa6c94d · outbound

This paper cites Evolving conceptions of memory storage, selective attention, and their mutual constraints within t he human information-processing system.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Evolving conceptions of memory storage, selective attention, and their mutual constraints within t he human information-processing system

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.678038Z

Source-reported events for the cited work

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

Observation 7df3325e-06e8-4e3c-94f4-970f5c8fe60d · outbound

This paper cites Gorillas in o ur midst: Sustained inattentional blindness for dynamic even ts.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Gorillas in o ur midst: Sustained inattentional blindness for dynamic even ts

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.667871Z

Source-reported events for the cited work

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

Observation 986f31a7-4b68-4462-a0fe-8ea12a53f39c · outbound

This paper cites A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.873451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f7290c-b168-4ce8-90ef-4e4180549252 · outbound

This paper cites Towards Reasoning in Large Language Models: A Survey.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Towards Reasoning in Large Language Models: A Survey

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.878552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b80c3c7-1390-4ca3-a541-0d9e7a71cb79 · outbound

This paper cites BLIP: Bootstrapping language-image pre-training for uni- ﬁed vision-language understanding and generation.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs BLIP: Bootstrapping language-image pre-training for uni- ﬁed vision-language understanding and generation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.657305Z

Source-reported events for the cited work

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

Observation 459e376f-6ea2-4216-ae39-b4cca2348859 · outbound

This paper cites Improved baselines with visual instruction tuning.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Improved baselines with visual instruction tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.646969Z

Source-reported events for the cited work

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

Observation cb17de36-5de2-44a5-a6a6-36a309a7d109 · outbound

This paper cites Visual instruction tuning.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Visual instruction tuning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.636455Z

Source-reported events for the cited work

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

Observation 0a196353-6970-48be-a561-6475df71fb37 · outbound

This paper cites Learn- ing transferable visual models from natural language super - vision.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Learn- ing transferable visual models from natural language super - vision

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.626114Z

Source-reported events for the cited work

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

Observation a730e3ca-6ed9-4f89-ba7c-313898b53c0f · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Gonzalez, Ion Stoica, and Eric P

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.615563Z

Source-reported events for the cited work

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

Observation 4ef69fd8-c8cf-428a-886e-69c097dd6643 · outbound

This paper cites LLaV A-NeXT: Improved reasoning, OCR, and world knowledge, January 2024.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LLaV A-NeXT: Improved reasoning, OCR, and world knowledge, January 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.605002Z

Source-reported events for the cited work

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

Observation 26db7f9b-4f97-4657-96ae-b30f1f594096 · outbound

This paper cites Chat-UniVi: Uniﬁed visual representation em- powers large language models with image and video un- derstanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Chat-UniVi: Uniﬁed visual representation em- powers large language models with image and video un- derstanding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.593509Z

Source-reported events for the cited work

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

Observation f88579e9-fa6d-4200-b263-d4b8af2eccfa · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.906942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2987bfbe-8160-4cc4-82e7-04dd86388976 · outbound

This paper cites LLaMA-VID: An image is worth 2 tokens in large language models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LLaMA-VID: An image is worth 2 tokens in large language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.582514Z

Source-reported events for the cited work

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

Observation 036ff4c6-2a4c-4f33-843f-ad7a63e79d0d · outbound

This paper cites Video-ChatGPT: Towards detailed video understanding via large vision and language models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Video-ChatGPT: Towards detailed video understanding via large vision and language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.571257Z

Source-reported events for the cited work

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

Observation bff15451-a104-4096-8d85-99a4a3608245 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs VideoChat: Chat-Centric Video Understanding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.918069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed335c6-8428-477c-bc0e-df5493f02079 · outbound

This paper cites Video-LLaMA: An instruction-tuned audio-visual language model for video u n- derstanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Video-LLaMA: An instruction-tuned audio-visual language model for video u n- derstanding

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.560231Z

Source-reported events for the cited work

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

Observation be4ece27-1405-4655-a5b2-eb40b3fd5212 · outbound

This paper cites Long Context Transfer from Language to Vision.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Long Context Transfer from Language to Vision

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.926246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e125a25d-9c3e-4c63-9e97-ce526d0e041f · outbound

This paper cites MM-VID: Advancing Video Understanding with GPT-4V(ision).

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs MM-VID: Advancing Video Understanding with GPT-4V(ision)

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.930220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11af3d05-e190-49d4-a95f-e93605ad857d · outbound

This paper cites Artemis: Towards referential understanding in com- plex videos.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Artemis: Towards referential understanding in com- plex videos

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.549077Z

Source-reported events for the cited work

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

Observation bc2997e8-fe62-4226-ad6f-73f01a0bf2e9 · outbound

This paper cites Language Modeling Is Compression.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Language Modeling Is Compression

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.938041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e2a817-ff0d-4bcc-9ac4-056c70b034ba · outbound

This paper cites Learning to compress prompts with gist tokens.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Learning to compress prompts with gist tokens

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.537249Z

Source-reported events for the cited work

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

Observation 8b0d3a57-a938-4473-8bb8-46d60f090cc9 · outbound

This paper cites Adapting Language Models to Compress Contexts.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Adapting Language Models to Compress Contexts

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.944973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1b7ba47-f645-4d15-b8d6-c635ace6a03e · outbound

This paper cites In-context autoencoder for context compression in a large language model.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs In-context autoencoder for context compression in a large language model

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.524994Z

Source-reported events for the cited work

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

Observation 44a69e30-3231-4489-b71d-c1e357755cd6 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.952139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36121cd2-b067-4a17-8c4e-862db36d924b · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll´ ar, and C.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll´ ar, and C

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.512853Z

Source-reported events for the cited work

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

Observation c8122340-37a4-493e-8b54-e86355b4bda8 · outbound

This paper cites GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.959092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee9f54a9-fe60-4ab9-8322-2a6126eb3595 · outbound

This paper cites Towards VQA models that can read.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Towards VQA models that can read

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.501402Z

Source-reported events for the cited work

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

Observation b91841aa-e94c-484e-b18d-581ad71db4a4 · outbound

This paper cites OCR-VQA: Visual question answer- ing by reading text in images.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs OCR-VQA: Visual question answer- ing by reading text in images

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.490420Z

Source-reported events for the cited work

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

Observation a44ff3c8-5ee0-4ec5-9ba8-30e9cc4b7686 · outbound

This paper cites Shamma, Michael S.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Shamma, Michael S

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.479193Z

Source-reported events for the cited work

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

Observation 5df1571a-4fb6-460c-8846-abbf364b02a8 · outbound

This paper cites ActivityNet: A large-scale video benchmark for human activity understanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs ActivityNet: A large-scale video benchmark for human activity understanding

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.467827Z

Source-reported events for the cited work

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

Observation 22b0ec88-4294-43cb-830d-f43a972b8534 · outbound

This paper cites Decoupled weight de- cay regularization.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Decoupled weight de- cay regularization

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.977785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d500fb90-886e-4633-8b52-c1f4a61a9da6 · outbound

This paper cites In- ﬁniBench: A comprehensive benchmark for large multi- modal models in very long video understanding.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs In- ﬁniBench: A comprehensive benchmark for large multi- modal models in very long video understanding

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.981107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 830fac7b-03d5-4a5c-93ae-870ead615c7a · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs MLVU: Benchmarking Multi-task Long Video Understanding

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.984462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c017d31-1616-4b52-9b68-3eff82284fd9 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LVBench: An Extreme Long Video Understanding Benchmark

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.988258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ca34d3-ca2a-4c55-a4e3-523c1cb8ff76 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs NExT-QA: Next phase of question-answering to explaining temporal actions

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.449957Z

Source-reported events for the cited work

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

Observation daf2b5a1-113b-455b-aa4c-32eaa5c58fdf · outbound

This paper cites Video question answer- ing via gradually reﬁned attention over appearance and mo- tion.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Video question answer- ing via gradually reﬁned attention over appearance and mo- tion

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.437540Z

Source-reported events for the cited work

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

Observation 6ccf13c5-6b7b-4808-8755-2956f5e49417 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:50.998994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18562d97-8e0a-4fd6-ba9e-ff9b5af20b43 · outbound

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

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T16:39:51.002585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb3bfd6e-af12-462e-8e2e-3dc2546552d4 · outbound

This paper cites Sheldon,.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Sheldon,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.425862Z

Source-reported events for the cited work

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

Observation 45e7e380-d35e-46e5-b4aa-40a29260f057 · outbound

This paper cites Invisible Gorilla.

IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs Invisible Gorilla

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:39:51.414569Z

Source-reported events for the cited work

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

Coverage vector

Reference resolution

Outbound references

Pith citing papers