Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T18:38:49.654073Z
Paper Citation Record · LEDGER
Small Vision-Language Models are Smart Compressors for Long Video Understanding
As of 5 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 3 inbound Pith citation observations for arXiv:2604.08120.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T12:34:49.503345Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-04T16:39:58.308940Z
Reference resolution
19 of 19 outbound references displayed
- verified exact13
- verified fuzzy2
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch4
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 5016fc86-0c22-4adc-9087-09269cfb3ac9 · outbound
This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.
Small Vision-Language Models are Smart Compressors for Long Video Understanding LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T10:53:26.698662Z
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 15654cec-49c7-4dcc-9a56-4e5efd52163e · outbound
This paper cites Qwen3-VL Technical Report.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Qwen3-VL Technical Report
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T00:15:51.411232Z
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 23dc9d6e-a508-41c4-8002-33e500dbf78f · outbound
This paper cites Token Merging: Your ViT But Faster.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Token Merging: Your ViT But Faster
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T20:52:10.541797Z
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 ebdf246f-1770-4559-aedb-8b6979b1ba8a · outbound
This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.
Small Vision-Language Models are Smart Compressors for Long Video Understanding LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T03:51:25.572615Z
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 bbb71538-5646-4cfd-a29b-a210acff541f · outbound
This paper cites VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction.
Small Vision-Language Models are Smart Compressors for Long Video Understanding VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T21:08:19.955297Z
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 bac8378f-1dcf-4ea1-80f5-17e308c2061a · outbound
This paper cites LLaVA-OneVision: Easy Visual Task Transfer.
Small Vision-Language Models are Smart Compressors for Long Video Understanding LLaVA-OneVision: Easy Visual Task Transfer
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T00:15:51.503186Z
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 5b5c2f86-b199-40b1-8833-b6aca8febd81 · outbound
This paper cites Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:36:21.368649Z
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 e2f84104-be0e-42d7-a0af-20076b606867 · outbound
This paper cites VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling.
Small Vision-Language Models are Smart Compressors for Long Video Understanding VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T04:02:43.915683Z
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 d1c7aabf-cc5c-4e9e-adc7-4a15863bba87 · outbound
This paper cites Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T00:15:51.479344Z
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 9e82f47e-e342-4b7d-bd14-ba9df894202e · outbound
This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.
Small Vision-Language Models are Smart Compressors for Long Video Understanding LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Reference 10
- Resolution
- verified exact
- 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 b54d1c26-5e3f-447c-9cc0-dd3b4fc58135 · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T00:15:51.348826Z
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 272b9161-9183-4ac1-86ec-d7f8351168c3 · outbound
This paper cites Kimi-VL Technical Report.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Kimi-VL Technical Report
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T01:06:31.748869Z
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 a83564dd-7166-4d12-abe7-a59f17ccce1b · outbound
This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.
Small Vision-Language Models are Smart Compressors for Long Video Understanding InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T00:15:51.305763Z
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 e9615c1b-4e71-41ac-8a87-31575d9d8efd · outbound
This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.
Small Vision-Language Models are Smart Compressors for Long Video Understanding PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:21:58.165262Z
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 9f3d8f39-a4e4-4d9a-b896-eb99a658f92e · outbound
This paper cites VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding.
Small Vision-Language Models are Smart Compressors for Long Video Understanding VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T01:20:00.737157Z
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 1afa61d7-cf5c-414e-8e85-80ff3c064867 · outbound
This paper cites Video-llama: An instruction-tuned audio-visual language model for video understanding.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Video-llama: An instruction-tuned audio-visual language model for video understanding
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T16:58:08.257334Z
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 0d36e27f-b624-4232-8a0a-6456a6de7a6a · outbound
This paper cites Long Context Transfer from Language to Vision.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Long Context Transfer from Language to Vision
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:08:36.726593Z
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 827b03d8-05d5-45ca-aff9-982f7ca22373 · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
Small Vision-Language Models are Smart Compressors for Long Video Understanding MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T00:15:51.364401Z
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 37b4dd1a-7f7b-415c-a9b8-f17d61feed4a · outbound
This paper cites Because the sampled frame count for LVBench is fixed atfmax, the resulting upper bounds are4096/1024 = 4and12288 /2048 = 6tokens per frame, respectively.
Small Vision-Language Models are Smart Compressors for Long Video Understanding Because the sampled frame count for LVBench is fixed atfmax, the resulting upper bounds are4096/1024 = 4and12288 /2048 = 6tokens per frame, respectively
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T16:58:08.260550Z
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 11f6c408-8efc-44f9-9362-086b0115b8c7 · inbound
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence cites this paper.
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence Small Vision-Language Models are Smart Compressors for Long Video Understanding
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T22:13:59.629109Z
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 f30a5792-c856-4639-8d9c-b4eeb21cf9ec · inbound
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding cites this paper.
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding Small Vision-Language Models are Smart Compressors for Long Video Understanding
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T16:39:58.310762Z
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 9e7564e6-cb44-4e9f-bbf1-0467e2f29157 · inbound
BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics cites this paper.
BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics Small Vision-Language Models are Smart Compressors for Long Video Understanding
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T12:34:49.503345Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.