Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-15T18:25:21.621268Z
Paper Citation Record · LEDGER
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
As of 7 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 2 inbound Pith citation observations for arXiv:2603.01400.
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 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-13T05:49:36.807884Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-13T05:52:22.302025Z
Reference resolution
84 of 84 outbound references displayed
- verified exact34
- verified fuzzy50
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 7c10f71f-402b-4d28-871f-b86f7a71bebe · outbound
This paper cites GPT-4 Technical Report.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models GPT-4 Technical Report
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.912056Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1253536a-4a15-4c1e-8aee-7b006f87ad0f · outbound
This paper cites Flamingo: a visual language model for few-shot learning.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Flamingo: a visual language model for few-shot learning
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.377182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1055f925-b328-461c-b4ae-ae9e7c4202ec · outbound
This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.935702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f8cb1e64-111b-4df6-b4c1-364fc4cc487a · outbound
This paper cites Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.298589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1974daac-f804-45c3-bfe7-fdf8eed4ac00 · outbound
This paper cites Qwen2.5-VL Technical Report.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Qwen2.5-VL Technical Report
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.956008Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 69462350-8708-4509-97f6-41300568aaa4 · outbound
This paper cites Token Merging: Your ViT But Faster.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Token Merging: Your ViT But Faster
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:27.061121Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 307b969c-1c54-4663-83d5-2209560690f9 · outbound
This paper cites AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.013397Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ba2e3575-e5bf-49a5-ac5c-d197410f1676 · outbound
This paper cites Sharegpt4video: Improving video understand- ing and generation with better captions.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Sharegpt4video: Improving video understand- ing and generation with better captions
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.280286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bd15f5b5-a452-4350-a714-280ea226f9e8 · outbound
This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.293304Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4e4871fc-92c5-47fb-bab8-9107a70e4b50 · outbound
This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.277559Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5df7632b-e571-4beb-bf7b-51967f4adc3a · outbound
This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.978538Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ee3ff07b-972b-45f9-bd2a-785c6d92e094 · outbound
This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.344774Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cd2cbf18-b934-4781-a422-e2a96b0501eb · outbound
This paper cites Sinkhorn distances: Lightspeed computation of optimal transport.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Sinkhorn distances: Lightspeed computation of optimal transport
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.261925Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6e9f6adb-3187-4cd9-92eb-39f2b6bde528 · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.996414Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 46372f6a-4618-4cca-b194-81b6f406c0a5 · outbound
This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.274073Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f2b099df-6088-4428-8865-d4a635427214 · outbound
This paper cites FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:26.952439Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 352f6555-5169-49e5-ab23-c28f34d52a3b · outbound
This paper cites PruneVid: Visual Token Pruning for Efficient Video Large Language Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models PruneVid: Visual Token Pruning for Efficient Video Large Language Models
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:26.984952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dff2baec-d180-4d96-9c24-da12c23c0a9b · outbound
This paper cites Chat-univi: Unified visual representation em- powers large language models with image and video under- standing.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Chat-univi: Unified visual representation em- powers large language models with image and video under- standing
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.290323Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4478dee3-eee3-4428-a230-199ad501ce69 · outbound
This paper cites Sparsevila: Decoupling visual sparsity for efficient vlm inference.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Sparsevila: Decoupling visual sparsity for efficient vlm inference
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.322490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3dd5e7e3-2fbb-44dd-af9b-fa21596f9abb · outbound
This paper cites arXiv preprint arXiv:2505.18227 , year=.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models arXiv preprint arXiv:2505.18227 , year=
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.056369Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 428ecb9f-3562-4fb6-8fa0-dfa92f52b5a5 · outbound
This paper cites Lmms-eval: Accelerating the develop- ment of large multimoal models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Lmms-eval: Accelerating the develop- ment of large multimoal models
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.308834Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8865f885-a212-4fcb-8ffe-17891dd57711 · outbound
This paper cites LLaVA-OneVision: Easy Visual Task Transfer.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models LLaVA-OneVision: Easy Visual Task Transfer
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:27.041003Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 686986fc-58d7-4137-9653-ee300307b388 · outbound
This paper cites Expansion and shrinkage of localization for weakly- supervised semantic segmentation.NeurIPS, 35:16037– 16051.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Expansion and shrinkage of localization for weakly- supervised semantic segmentation.NeurIPS, 35:16037– 16051
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.328858Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a2ef54d3-0c89-4a57-8c38-d213e13a7912 · outbound
This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.325630Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 21ee01fe-f803-4313-ba9f-37ff6aef794d · outbound
This paper cites Cross-modal and uncertainty-aware agglomeration for open- vocabulary 3d scene understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Cross-modal and uncertainty-aware agglomeration for open- vocabulary 3d scene understanding
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.240097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dfa922e3-a8f2-4bc4-9a88-33451116a8f3 · outbound
This paper cites Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:26.948407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b81222d6-1c0c-456b-a895-5978774aac55 · outbound
This paper cites VideoChat: Chat-Centric Video Understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models VideoChat: Chat-Centric Video Understanding
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.928192Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d3c1fd37-8662-4bbe-95d9-8e16c98864c8 · outbound
This paper cites Mvbench: A comprehensive multi-modal video understand- ing benchmark.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Mvbench: A comprehensive multi-modal video understand- ing benchmark
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.311328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0ca99f3f-3ac6-469b-b433-50a8ad459118 · outbound
This paper cites Llama-vid: An image is worth 2 tokens in large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Llama-vid: An image is worth 2 tokens in large language models
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.237289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1cc47a42-5cb6-4f36-90de-b608a721c1cc · outbound
This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.944119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 50387c75-1d4d-413c-9df0-f1c51e32d1cc · outbound
This paper cites Vila: On pre-training for visual language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Vila: On pre-training for visual language models
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.242622Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 97643793-6fb5-42a3-85e4-f8ab4c8720ae · outbound
This paper cites Improved baselines with visual instruction tuning.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Improved baselines with visual instruction tuning
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.331859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 333756eb-327e-4182-94d1-986f82bd549f · outbound
This paper cites Llavanext: Improved reasoning, ocr, and world knowledge.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Llavanext: Improved reasoning, ocr, and world knowledge
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.316806Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c04c2190-6cf4-4248-a223-772acb2fbd56 · outbound
This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:26.920542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f78afe71-546c-4bf0-832f-bfe4925584b2 · outbound
This paper cites Less: Label-efficient and single-stage referring 3d instance segmentation.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Less: Label-efficient and single-stage referring 3d instance segmentation
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.228851Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dd783566-e8cb-4ea9-8c0f-855c4dcb10c8 · outbound
This paper cites Hybrid-level instruction injection for video token com- pression in multi-modal large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Hybrid-level instruction injection for video token com- pression in multi-modal large language models
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.271560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4b253035-c0cc-4c9a-ad00-75b558830e2b · outbound
This paper cites Nvila: Efficient frontier visual language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Nvila: Efficient frontier visual language models
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.256555Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 119419f0-a3c9-4320-aa07-95ed7de6e61f · outbound
This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.991401Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d8d0dbef-36dc-4286-85f0-503ff62da652 · outbound
This paper cites Egoschema: A diagnostic benchmark for very long- form video language understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Egoschema: A diagnostic benchmark for very long- form video language understanding
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.248078Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f2727595-b486-495a-9b65-2650249c2315 · outbound
This paper cites Perla: Perceptive 3d language assistant.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Perla: Perceptive 3d language assistant
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.362604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 08caf57a-46e1-4c13-a6bc-39a19e2ebb52 · outbound
This paper cites M ´emoire sur la th ´eorie des d ´eblais et des remblais.Mem.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models M ´emoire sur la th ´eorie des d ´eblais et des remblais.Mem
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.365862Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 87e95e8c-7ad4-4f95-af23-b688b1630d64 · outbound
This paper cites T2td: Text-3d generation model based on prior knowledge guidance.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1):172–189.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models T2td: Text-3d generation model based on prior knowledge guidance.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1):172–189
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.352537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fad83d17-fa96-4fb7-add5-f142e4908837 · outbound
This paper cites Learn- ing transferable visual models from natural language super- vision.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Learn- ing transferable visual models from natural language super- vision
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.359194Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d1ae580b-a2b5-4911-9389-01680269bb93 · outbound
This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Llava-prumerge: Adaptive token reduction for efficient large multimodal models
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.373553Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bd723006-e8a7-4702-afa8-a3c10793bff8 · outbound
This paper cites arXiv preprint arXiv:2505.21334 , year=.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models arXiv preprint arXiv:2505.21334 , year=
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.018134Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e6373ec4-0774-4ee1-8c9a-40bb5e22f222 · outbound
This paper cites TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
Reference 46
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.050959Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6bbf309f-ade3-41ff-a155-ff5a2fe005b9 · outbound
This paper cites Fastvid: Dynamic density pruning for fast video large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Fastvid: Dynamic density pruning for fast video large language models
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.024250Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9bc14500-af25-4c75-9f31-cda3689159b6 · outbound
This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Reference 48
- 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 2026-08-07T06:34:17.273281+00:00.
Observation bfa32464-5aad-4bc0-9041-c8da6c5b5c72 · outbound
This paper cites Moviechat: From dense token to sparse memory for long video understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Moviechat: From dense token to sparse memory for long video understanding
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.334653Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 989474e8-b56d-4783-82f1-5a2c5cb5ac92 · outbound
This paper cites TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.066331Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7588e5c2-9c25-4a18-8251-fd0d9493dfd5 · outbound
This paper cites Dycoke: Dynamic compression of tokens for fast video large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Dycoke: Dynamic compression of tokens for fast video large language models
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.337712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 52a2c208-bf56-4fd8-a039-25a8e104e1ea · outbound
This paper cites Stanford alpaca: An instruction-following llama model.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Stanford alpaca: An instruction-following llama model
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.340873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 13e0de41-33bf-4729-85de-bf7be3322db2 · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Gemini: A Family of Highly Capable Multimodal Models
Reference 53
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.924185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 27654a1b-7146-4301-a713-b381a7990ea8 · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 54
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.931899Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 31b238ec-1cb4-4325-8768-9d21905c70d2 · outbound
This paper cites Introduction to optimal transport.Notes of Course at University of Cambridge, 3.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Introduction to optimal transport.Notes of Course at University of Cambridge, 3
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.234249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d5e2a7a3-8853-4cc8-93b2-0d7d378f2015 · outbound
This paper cites Springer.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Springer
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.253693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 41ed44ae-c1df-4774-9b91-4580736da2aa · outbound
This paper cites Ross3d: Re- constructive visual instruction tuning with 3d-awareness.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Ross3d: Re- constructive visual instruction tuning with 3d-awareness
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.314206Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5763ab29-2d37-442c-86c7-bfe7cc13504d · outbound
This paper cites ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.035766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e54f96a9-a8cd-4e1e-8374-b0af4b18f2b0 · outbound
This paper cites Uvmap-id: A controllable and personalized uv map generative model.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Uvmap-id: A controllable and personalized uv map generative model
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.370028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fa469ff6-c5a0-423b-a471-560860c4103d · outbound
This paper cites Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
Reference 60
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.002398Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 936eb09b-3111-47d2-a29e-0e6f8d874e28 · outbound
This paper cites Longvlm: Efficient long video understand- ing via large language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Longvlm: Efficient long video understand- ing via large language models
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.267065Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0233a267-69d2-4fe4-8eb5-4edf7cdeec25 · outbound
This paper cites Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Reference 62
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.964302Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a5f3a305-0905-4ffe-9d69-5e604be1e28e · outbound
This paper cites Longvideobench: A benchmark for long-context interleaved video-language understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Longvideobench: A benchmark for long-context interleaved video-language understanding
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.284735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2037e54b-31c8-416e-b5fc-ae29cfee9e3a · outbound
This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Reference 64
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.974162Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dc8c9f21-d6f1-439f-9ab8-4caacc9ff7d8 · outbound
This paper cites Conical visual concentration for efficient large vision-language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Conical visual concentration for efficient large vision-language models
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.287311Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6c7c6dd1-3510-4128-a3f6-85ee4a6f7e05 · outbound
This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Reference 66
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 910a5ad1-c5bd-4f2a-bf96-d8646a932163 · outbound
This paper cites Topv: Compatible token pruning with infer- ence time optimization for fast and low-memory multimodal vision language model.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Topv: Compatible token pruning with infer- ence time optimization for fast and low-memory multimodal vision language model
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.231490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6bb79c97-e5cc-467c-9eff-f274ef67b8d8 · outbound
This paper cites Visionzip: Longer is better but not necessary in vision language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Visionzip: Longer is better but not necessary in vision language models
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.301957Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9b795a22-c186-4d82-9ceb-07e2ef51ca43 · outbound
This paper cites Atp-llava: Adaptive token pruning for large vision language models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Atp-llava: Adaptive token pruning for large vision language models
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.319661Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 497c6d8d-8b7b-422b-a3cc-707d95f77df8 · outbound
This paper cites Video question answering with prior knowledge and object-sensitive learning.IEEE Transactions on Image Processing, 31:5936–5948.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video question answering with prior knowledge and object-sensitive learning.IEEE Transactions on Image Processing, 31:5936–5948
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.269399Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 19451f1f-e827-4dee-9245-d8da96bf0313 · outbound
This paper cites Sigmoid loss for language image pre-training.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Sigmoid loss for language image pre-training
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.251311Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7accfd02-4002-4099-bac7-57c4f08f4157 · outbound
This paper cites arXiv preprint arXiv:2505.22654 , year=.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models arXiv preprint arXiv:2505.22654 , year=
Reference 72
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:27.008012Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1fa2b1de-1857-4a5b-ae05-2bf9db620fb5 · outbound
This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:27.046262Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation da801dc0-aab0-4ce9-ad44-52e5365121a7 · outbound
This paper cites Omnicharacter: Towards immersive role- playing agents with seamless speech-language personality interaction.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Omnicharacter: Towards immersive role- playing agents with seamless speech-language personality interaction
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.356002Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d6442c55-87c2-4295-8a0d-5f0a1c26eeb9 · outbound
This paper cites Text-video re- trieval with global-local semantic consistent learning.IEEE Transactions on Image Processing.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Text-video re- trieval with global-local semantic consistent learning.IEEE Transactions on Image Processing
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.259230Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0360cb4f-239e-43ce-a38b-344b429992d2 · outbound
This paper cites Lmms-eval: Re- ality check on the evaluation of large multimodal models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Lmms-eval: Re- ality check on the evaluation of large multimodal models
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.348659Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6d743b53-706a-4d33-b0e2-5707633b4264 · outbound
This paper cites [cls] attention is all you need for training-free visual token pruning: Make vlm inference faster.arXiv e- prints, pages arXiv–2412.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models [cls] attention is all you need for training-free visual token pruning: Make vlm inference faster.arXiv e- prints, pages arXiv–2412
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.245048Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6d510b01-19d4-4d2f-8829-9cf4b29286e2 · outbound
This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Reference 78
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:27.029877Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3630be8a-844e-43a2-a638-af0d7ff4f7fd · outbound
This paper cites Llava- next: A strong zero-shot video understanding model.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Llava- next: A strong zero-shot video understanding model
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.264782Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 29b998a0-8613-4a1a-a67d-e000e269443c · outbound
This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models LLaVA-Video: Video Instruction Tuning With Synthetic Data
Reference 80
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:26.969533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 32f9a511-da57-4916-ac08-9d42fb29f604 · outbound
This paper cites Video-3d llm: Learning position-aware video representation for 3d scene understanding.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Video-3d llm: Learning position-aware video representation for 3d scene understanding
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.295927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bf521ba6-1604-4758-b59a-e5446d40d410 · outbound
This paper cites LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
Reference 82
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:26:26.916148Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0c57d810-ae1e-4d7e-81fc-2223d5a8a1ef · outbound
This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Reference 83
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:26:27.070691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 07e72e4f-10d8-46c3-b257-6b3bfdb52187 · outbound
This paper cites Apollo: An explo- ration of video understanding in large multimodal models.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models Apollo: An explo- ration of video understanding in large multimodal models
Reference 84
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T18:26:27.306236Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
Observation d4204f00-7efd-4621-a236-4d9caf0f85ab · inbound
PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems cites this paper.
PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T08:58:12.746045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e38e845a-639f-486f-8083-1956331cd973 · inbound
OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models cites this paper.
OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T05:52:22.303693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.