Paper Citation Record · LEDGER

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

As of 5 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 13 inbound Pith citation observations for arXiv:2601.14724.

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

pith.paper-citation-record.v1
2601.14724 v4

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T12:55:04.564442Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:24:16.121151Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T12:09:48.861966Z

Reference resolution

56 of 56 outbound references displayed

verified exact40
verified fuzzy10
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eeefd53d-e0b5-4f98-8fbf-e0017f999331 · outbound

This paper cites Claude 3.5 sonnet.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Claude 3.5 sonnet

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.430090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6c73279b-806e-4a4d-9a57-9db91dd32821 · outbound

This paper cites Atkinson and R.M.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Atkinson and R.M

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.432800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2c83fdc4-308f-4cb9-9b94-ed37b14cfb63 · outbound

This paper cites an unresolved cited work.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-16T12:57:54.448507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cabb502f-7ce8-4f7c-92e6-20e31458f223 · outbound

This paper cites Baddeley and Graham Hitch.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Baddeley and Graham Hitch

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.420947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 70df9ede-de91-42c0-a414-7f8b96845227 · outbound

This paper cites Qwen3-VL Technical Report.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Qwen3-VL Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.908356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c030607d-b495-451c-b085-053afa3546d3 · outbound

This paper cites Qwen2.5-VL Technical Report.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Qwen2.5-VL Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.971715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 007cc5c6-158d-4843-96b9-1e82af710733 · outbound

This paper cites Titans: Learning to Memorize at Test Time.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Titans: Learning to Memorize at Test Time

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.975270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fed96e5a-87f0-4260-884c-d4087dd1756b · outbound

This paper cites VideoLLM-online: Online Video Large Language Model for Streaming Video.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding VideoLLM-online: Online Video Large Language Model for Streaming Video

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.856695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 34e9df43-e14f-445a-96b6-6be4e86c103a · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Stream- ingtom: Streaming token compression for efficient video un- derstanding

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.882760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2ef11b82-c427-48f5-a06a-29a9c2e1e9ae · outbound

This paper cites arXiv preprint arXiv:2511.07278 , year=.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding arXiv preprint arXiv:2511.07278 , year=

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:57:53.823325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 44b267b5-78da-4a54-98f9-d17b9143b795 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.921405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation feca7946-f607-4e82-9756-6fe719286aea · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.900078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3db7d4dd-4193-4ee2-af66-4d7f950becb9 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.895827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fdac2be5-65b6-448f-8898-94b65a3e1724 · outbound

This paper cites Streaming Video Question-Answering with In-context Video KV-Cache Retrieval.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streaming Video Question-Answering with In-context Video KV-Cache Retrieval

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.956540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 82104efb-e7b6-4c6a-a83f-034e1cac68d2 · outbound

This paper cites Memory: A contribution to experimental psychology.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Memory: A contribution to experimental psychology

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.438105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 890803af-01d2-449c-a2f7-626978946bee · outbound

This paper cites Video-ccam: Enhancing video-language understanding with causal cross-attention masks for short and long videos.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Video-ccam: Enhancing video-language understanding with causal cross-attention masks for short and long videos

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.427366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 58748ca8-f6e4-4b6f-88d7-5929ef0962e8 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.964477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8c87d7b7-da7a-4fbd-8e8c-70ae44d96a13 · outbound

This paper cites Ego4D: Around the World in 3,000 Hours of Egocentric Video.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Ego4D: Around the World in 3,000 Hours of Egocentric Video

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.819073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e019c0bd-8595-4c25-bb6d-e3170c9cace1 · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.982616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b3f5d12b-8e79-4b6f-adec-88619d778632 · outbound

This paper cites Memory in the Age of AI Agents.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Memory in the Age of AI Agents

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.943809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 596cf76f-bcf8-490d-bce8-5565ccfad14c · outbound

This paper cites MovieNet: A Holistic Dataset for Movie Understanding.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding MovieNet: A Holistic Dataset for Movie Understanding

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.960327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 51394f83-e005-4531-a029-9c6a5146d345 · outbound

This paper cites InfiniPot: Infinite Context Processing on Memory-Constrained LLMs.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding InfiniPot: Infinite Context Processing on Memory-Constrained LLMs

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.827708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f2b325d0-b592-4242-a870-d8a998c63cca · outbound

This paper cites Infinipot-v: Memory-constrained kv cache com- pression for streaming video understanding.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Infinipot-v: Memory-constrained kv cache com- pression for streaming video understanding

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.891568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fdb428ea-cf70-4938-a36a-6c4ecb1ab4d4 · outbound

This paper cites Llava-onevision: Easy visual task transfer.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Llava-onevision: Easy visual task transfer

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.445564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dec76cd9-6cc1-4bdc-b315-c7a48ee6782e · outbound

This paper cites MVBench: A Comprehensive Multi-modal Video Understanding Benchmark.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-17T20:22:35.388231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 64639c42-d365-455b-84b7-b22b794da0bd · outbound

This paper cites OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.869588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03fd888e-7c74-439c-9582-e6d7ba631392 · outbound

This paper cites VILA: On Pre-training for Visual Language Models.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding VILA: On Pre-training for Visual Language Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.836328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0e4d39fc-a2c3-4992-a246-21e09a9af8df · outbound

This paper cites Streamingbench: Assessing the gap for mllms to achieve streaming video understanding.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streamingbench: Assessing the gap for mllms to achieve streaming video understanding

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.435515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3db1b08f-2d8b-4279-a72b-1e0636a1f15b · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Llava-next: Improved reasoning, ocr, and world knowledge

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.424701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8313bc12-2f58-443d-87b3-565b183979ff · outbound

This paper cites Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.873910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 86434552-e4a1-40e7-b298-5d29ddd11a74 · outbound

This paper cites EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.948203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5ed47c81-1051-40a5-a7c8-62837a2f8c0b · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.904250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6e6375ef-3606-4b64-862d-c524d1fb7b6e · outbound

This paper cites GPT-4o System Card.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding GPT-4o System Card

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.848782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f4e937ae-bb78-4de8-a3ae-2459881d3ccc · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding MemGPT: Towards LLMs as Operating Systems

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T12:57:53.840439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3c68a8dd-bae2-424e-9ef6-57b524686eb7 · outbound

This paper cites Perception Test: A Diagnostic Benchmark for Multimodal Video Models.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Perception Test: A Diagnostic Benchmark for Multimodal Video Models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.852870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6362aea4-172e-4120-8ee6-f36894c11b30 · outbound

This paper cites Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.912952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9036f4a4-0d06-4363-b275-d80103f7e919 · outbound

This paper cites NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.952237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3826a984-a7f4-4ced-ae51-652b23a95305 · outbound

This paper cites Cognitive Memory in Large Language Models.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Cognitive Memory in Large Language Models

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:57:53.990059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a98ebbc7-2db3-40b5-92f2-def2c0edfa2f · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T13:53:33.725971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a2128ac5-4dc8-4a60-acb3-4a2d9c4f98da · outbound

This paper cites Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.809989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b08a16f-941a-4a64-8f19-744306d50b72 · outbound

This paper cites DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.927169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d6b90fdf-30db-4e8c-9abd-c6d583ec1412 · outbound

This paper cites Streambridge: Turning your offline video large language model into a proactive streaming assistant.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streambridge: Turning your offline video large language model into a proactive streaming assistant

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.831831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 476a5a0c-e658-47ab-9889-1366d360a8d6 · outbound

This paper cites Dynamic-vlm: Simple dynamic visual token compression for videollm.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Dynamic-vlm: Simple dynamic visual token compression for videollm

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.451880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 29d6dc38-c57d-461f-bb7c-12a29c09fe52 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.968230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5f1de1df-84e0-4e28-bce3-6e91b5a6de45 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.878322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 10b406f3-de90-4880-aaa4-951d4684bfcd · outbound

This paper cites Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.814670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6c17c7e-b2ec-4310-a3e3-3796ecbdb388 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding StreamingVLM: Real-Time Understanding for Infinite Video Streams

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:51:33.451476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8b0a0d65-411c-44ad-981c-e1360292c619 · outbound

This paper cites StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.939593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db91a4c5-2860-4117-9e7c-b12a377fdd75 · outbound

This paper cites Visionzip: Longer is better but not necessary in vision language models.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Visionzip: Longer is better but not necessary in vision language models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.887328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a862863e-3446-48f2-8225-ec78e055dbe8 · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.993597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 11abff98-bfa7-4491-9d0d-7670db5d6b1e · outbound

This paper cites TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.845048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6fd65a51-7f34-4024-aeea-8907c4eb203c · outbound

This paper cites Streamforest: Efficient online video understanding with persistent event memory.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streamforest: Efficient online video understanding with persistent event memory

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:57:54.442053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ad8191f-d155-4f05-a614-629215b5949b · outbound

This paper cites Streamforest: Efficient online video understanding with persistent event memory.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Streamforest: Efficient online video understanding with persistent event memory

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.917416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 22a96c46-ffa6-459c-a1f9-b95b727ad2cb · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.864829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ff464fde-2c93-413f-85b0-02642e352f9f · outbound

This paper cites Long Context Transfer from Language to Vision.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Long Context Transfer from Language to Vision

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:57:53.860496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8e80d361-9caf-4698-a92a-d715b48a041d · outbound

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

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 57

Resolution: malformed identifier; local_arxiv, observed 2026-05-16T12:57:53.935463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation a5039699-9c3f-488e-ae47-0640d570164f · inbound

VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models cites this paper.

VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:11:13.681304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9888cebf-3702-4571-b03c-8ec4b3f3ee2c · inbound

Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding cites this paper.

Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-11T03:50:56.380773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 982963f1-25ae-4d72-bcbf-69094a119b62 · inbound

EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision cites this paper.

EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-06-28T22:42:46.367821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 938730a4-2fad-4209-a227-1d726c4c523f · inbound

Linear Scaling Video VLMs for Long Video Understanding cites this paper.

Linear Scaling Video VLMs for Long Video Understanding HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 80

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T23:02:46.250562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 63b23346-2c99-4ab1-b812-7df47e421337 · inbound

OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs cites this paper.

OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:16:27.082560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 350146db-d5f0-4a42-82c9-553310b200d2 · inbound

Harnessing Streaming Video in the Wild cites this paper.

Harnessing Streaming Video in the Wild HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:37:25.699669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2cbe530f-ceb4-4ee7-bac4-5fae17998bcf · inbound

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference cites this paper.

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T03:19:29.896742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 311c7af6-c71b-4ebb-892b-1c9ec32b3021 · inbound

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse cites this paper.

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 52

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T12:09:48.863194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1fab58bf-3224-4412-add9-4d877e13272f · inbound

FOLIO: Focused Semantic Memory for Streaming Video Understanding cites this paper.

FOLIO: Focused Semantic Memory for Streaming Video Understanding HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T05:40:49.468513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4feeb3-aec0-4ae2-bbb9-7012c9f0416f · inbound

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning cites this paper.

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T12:28:00.825262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 545c03c7-662e-4940-ad74-f9d562effd61 · inbound

EgoPlay: Event-Triggered Video Editing for Egocentric Streams cites this paper.

EgoPlay: Event-Triggered Video Editing for Egocentric Streams HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 111

Resolution: unresolved; no resolver link, observed 2026-07-31T11:46:42.281851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6646d2c-2b96-4cac-90eb-6ff616bfe3d6 · inbound

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding cites this paper.

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T03:21:48.390988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2841afe3-39a4-481c-bd96-9094add4e35c · inbound

AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning cites this paper.

AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T17:24:16.121151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.