MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering | Paper Citation Record

Observation f48a51dc-6644-4799-abfc-ded2c76cc6ac · outbound

This paper cites Flamingo: a visual language model for few-shot learning.NeurIPS, 35: 23716–23736.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Flamingo: a visual language model for few-shot learning.NeurIPS, 35: 23716–23736

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.518829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d79c84ca-d52d-41a6-8ff8-d6cf64f156f7 · outbound

This paper cites Qwen3-VL Technical Report.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Qwen3-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.171108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7313532e-d499-4156-833d-4fa4aebf9593 · outbound

This paper cites Qwen2.5-VL Technical Report.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.211109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 67f14717-b47b-48f1-bace-e605ee57cb6b · outbound

This paper cites Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.234731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 08211e91-7187-46fa-98b3-04232d970c51 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.635686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8556364b-d2cb-49f6-ab4f-836644a08bed · outbound

This paper cites Stream- ingtom: Streaming token compression for efficient video un- derstanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Stream- ingtom: Streaming token compression for efficient video un- derstanding

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.157633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e9abc9ae-0c01-40ee-bf20-a09172d12d3a · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Gonzalez, Ion Stoica, and Eric P

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.541807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bb0f27fe-7b0d-41db-a602-924e7b6910d0 · outbound

This paper cites An algorithm for the machine calculation of complex fourier series.Mathematics of computation, 19(90):297–301.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering An algorithm for the machine calculation of complex fourier series.Mathematics of computation, 19(90):297–301

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.545879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5aae5c93-d068-4aee-83e3-c8afed73c690 · outbound

This paper cites Streaming video question-answering with in-context video kv-cache retrieval.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Streaming video question-answering with in-context video kv-cache retrieval

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.650695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 786c6920-8039-4858-b5a3-56a8ab67c4d3 · outbound

This paper cites The llama 3 herd of models.arXiv e-prints, pages arXiv–2407.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering The llama 3 herd of models.arXiv e-prints, pages arXiv–2407

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.534445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a1511583-0714-4d33-8a52-8e03951bab0d · outbound

This paper cites Videoagent: A memory-augmented mul- timodal agent for video understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Videoagent: A memory-augmented mul- timodal agent for video understanding

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.530357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9afe74f7-d43d-481e-be94-175d877b771d · outbound

This paper cites an unresolved cited work.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Unresolved cited work

Reference 12

Resolution: parse uncertain; raw_fallback, observed 2026-05-22T07:21:14.538100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7348c682-6026-4180-b4d9-4720b17de7a6 · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.550053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fd5bebd7-5cbe-43d4-8f70-f5aacd5cea0c · outbound

This paper cites Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning.ICLR.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning.ICLR

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.522477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 66ff5f31-3f37-4b67-bec1-002ccbfd0d21 · outbound

This paper cites Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.526751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fdcbb041-873e-42a3-ad48-4a58e48cb870 · outbound

This paper cites GPT-4o System Card.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering GPT-4o System Card

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.253524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d7b9526d-fd9b-4e8f-bc47-5e37cdc0777b · outbound

This paper cites FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.141948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1198858a-1275-4c0f-8ccb-ebcea1cc33e3 · outbound

This paper cites Freqkv: Frequency domain key- value compression for efficient context window extension.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Freqkv: Frequency domain key- value compression for efficient context window extension

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.147333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c32ad5e0-704f-41ed-9201-ea322d728f4b · outbound

This paper cites Infinipot-v: Memory-constrained kv cache compres- sion for streaming video understanding.NeurIPS.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Infinipot-v: Memory-constrained kv cache compres- sion for streaming video understanding.NeurIPS

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.553283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8c3d3d4d-88e4-4f4f-9529-cf6f9424fe98 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering LLaVA-OneVision: Easy Visual Task Transfer

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.166616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c5799eed-7eb5-429c-a6ed-600f4c0a464f · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Mvbench: A comprehensive multi-modal video understand- ing benchmark

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.556925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4900905f-d1b9-4830-9a55-451bf3df74f9 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.205540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ff030c80-ab6b-4b45-ba45-c3975a3dddef · outbound

This paper cites StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.153199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 20bf36fa-d7e9-49b5-b497-d4e95c941b42 · outbound

This paper cites Freekv: Boosting kv cache retrieval for efficient llm inference.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Freekv: Boosting kv cache retrieval for efficient llm inference

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.191012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ddbfde8-7c09-4cdb-8d23-7e42aa394cc4 · outbound

This paper cites Cachegen: Kv cache com- pression and streaming for fast large language model serv- ing.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Cachegen: Kv cache com- pression and streaming for fast large language model serv- ing

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.643410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7969c3f8-41b1-48e7-8a5e-eca94aee438c · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.243711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6a612dde-440f-486e-af3c-80e3864da606 · outbound

This paper cites Egoschema: A diagnostic benchmark for very long- form video language understanding.Advances in Neural In- formation Processing Systems, 36:46212–46244.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Egoschema: A diagnostic benchmark for very long- form video language understanding.Advances in Neural In- formation Processing Systems, 36:46212–46244

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.631955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 285586a3-6d54-43cf-a36a-5e7003746a77 · outbound

This paper cites Morevqa: Exploring modular reason- ing models for video question answering.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Morevqa: Exploring modular reason- ing models for video question answering

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.628333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d48b7c7-e9dc-43fc-9759-88459a5e170f · outbound

This paper cites LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.215686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b7e7ee0a-073b-43ac-813f-daa36f9de4f7 · outbound

This paper cites Streaming long video understanding with large language models.NeurIPS, 37: 119336–119360.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Streaming long video understanding with large language models.NeurIPS, 37: 119336–119360

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.560478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d1aca159-7f11-4ca3-8591-21c2e03aa2f3 · outbound

This paper cites Dispider: Enabling video llms with active real-time interaction via dis- entangled perception, decision, and reaction.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Dispider: Enabling video llms with active real-time interaction via dis- entangled perception, decision, and reaction

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.621147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 43b82120-628a-41fc-8396-d8de75b65ee2 · outbound

This paper cites Question- answering dense video events.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Question- answering dense video events

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.624663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f4a8f6fd-ce67-428a-9ae4-8bd9fe2216e0 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.220539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f33e1d2f-db16-4f3f-b3d5-1382c9f93e9e · outbound

This paper cites Video-xl: Extra-long vision language model for hour-scale video understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video-xl: Extra-long vision language model for hour-scale video understanding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.606203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0af27a94-9b11-4271-95be-303332d1520b · outbound

This paper cites Moviechat+: Question-aware sparse memory for long video question answering.IEEE Transac- tions on Pattern Analysis and Machine Intelligence.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Moviechat+: Question-aware sparse memory for long video question answering.IEEE Transac- tions on Pattern Analysis and Machine Intelligence

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.610239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation be3c5e96-0714-44b6-a02a-6f6bdeb68a4d · outbound

This paper cites Razorattention: Ef- ficient kv cache compression through retrieval heads.ICLR.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Razorattention: Ef- ficient kv cache compression through retrieval heads.ICLR

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.617433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 56721c51-539e-4a84-83a1-7d1801205009 · outbound

This paper cites Fier: Fine-grained and efficient kv cache retrieval for long-context llm inference.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Fier: Fine-grained and efficient kv cache retrieval for long-context llm inference

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.225391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cf529906-fa32-4aab-b958-28592168f03a · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.239247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2dda01c6-f905-474d-b6e8-4ed73230c145 · outbound

This paper cites Videoagent: Long-form video understanding with large language model as agent.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Videoagent: Long-form video understanding with large language model as agent

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.613815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bf36e788-09c0-43e7-8528-2b51fd61e1ed · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.185135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fcb46db8-ca8e-4b40-8810-bbc67439016b · outbound

This paper cites Videochat-a1: Thinking with long videos by chain-of-shot reasoning.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Videochat-a1: Thinking with long videos by chain-of-shot reasoning

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.248852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c011934e-e4a6-4bcb-b1c5-839b29a33695 · outbound

This paper cites Videotree: Adaptive tree-based video representation for llm reasoning on long videos.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Videotree: Adaptive tree-based video representation for llm reasoning on long videos

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.602442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0d419aa-88e2-4df5-af3e-3e58681b2410 · outbound

This paper cites Longvlm: Efficient long video understand- ing via large language models.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Longvlm: Efficient long video understand- ing via large language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.598984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 69ea27b5-249d-4e79-93ec-380aaa7089fd · outbound

This paper cites Efficient streaming language models with attention sinks.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Efficient streaming language models with attention sinks

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.589088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 97b736e7-2cfd-4019-a811-bd6572a6b774 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Next-qa: Next phase of question-answering to explaining temporal actions

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.585766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 551801b3-427e-4510-8928-626f655cc50f · outbound

This paper cites Videoqa in the era of llms: An empirical study.International Journal of Computer Vi- sion, 133(7):3970–3993.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Videoqa in the era of llms: An empirical study.International Journal of Computer Vi- sion, 133(7):3970–3993

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.592604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 291d701a-1627-4e1f-af12-8960d57ab3e1 · outbound

This paper cites Unleashing the power of llms for medical video answer localization.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Unleashing the power of llms for medical video answer localization

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.578509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b49c3d7f-a602-4830-a94c-533543d45598 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video question answer- ing via gradually refined attention over appearance and mo- tion

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.573793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 55609626-adcd-46cd-88ff-eb6783f7d384 · outbound

This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.229626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cd37c81d-61b9-4404-a76b-cf719321fb94 · outbound

This paper cites StreamingVLM: Real-Time Understanding for Infinite Video Streams.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering StreamingVLM: Real-Time Understanding for Infinite Video Streams

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.201067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 99402878-9b5f-4874-aa84-faf21aaf5fc9 · outbound

This paper cites Qwen3 Technical Report.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Qwen3 Technical Report

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.180275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6628c57b-9336-400a-b86a-95d6822793db · outbound

This paper cites StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:21:13.162351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1e15930b-668f-4629-b693-018775e1bacf · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Activitynet-qa: A dataset for understanding complex web videos via question answering

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.570323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 51f1d8a0-4f7e-4669-b215-4aa338b27296 · outbound

This paper cites Socratic models: Composing zero-shot multimodal reasoning with language.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Socratic models: Composing zero-shot multimodal reasoning with language

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.581986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4b2eb10-8254-4afe-9eb6-bf7a245d332a · outbound

This paper cites VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.175600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3bacab6a-b5c9-4eed-8c17-e716b8d675c1 · outbound

This paper cites A simple llm framework for long-range video question-answering.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering A simple llm framework for long-range video question-answering

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.566770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 212bcabf-15f2-42fc-9d1f-28eae45cda23 · outbound

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

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.195740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d250c4d7-474d-49d6-9da9-2c345d28a825 · outbound

This paper cites Flash-vstream: Memory- based real-time understanding for long video streams.ICCV.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Flash-vstream: Memory- based real-time understanding for long video streams.ICCV

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.595603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cacf7c82-db82-4615-8625-563b629ee5cb · outbound

This paper cites Long Context Transfer from Language to Vision.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Long Context Transfer from Language to Vision

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:13.259289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad2eac76-8dcb-4c7f-a80c-2cb14fce30c7 · outbound

This paper cites Mlvu: Benchmarking multi-task long video understanding.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Mlvu: Benchmarking multi-task long video understanding

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.655074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 461620b9-6954-48d2-98df-5faed5f8a491 · outbound

This paper cites What is the person holding right now?.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering What is the person holding right now?

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:21:14.647143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8602b304-783d-4946-b1a4-d8ef17a4e380 · outbound

This paper cites an unresolved cited work.

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-05-22T07:21:14.563576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers