Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T14:40:23.771906Z
Paper Citation Record · LEDGER
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
As of 15 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 10 inbound Pith citation observations for arXiv:2411.15024.
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 2026-08-15T06:32:42.880941+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:08:09.432264Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-22T14:31:40.739574Z
Reference resolution
56 of 56 outbound references displayed
- verified exact0
- verified fuzzy23
- unresolved33
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 530f79c1-4e59-4f8a-8606-9bd9662b71ca · outbound
This paper cites Token Merging: Your ViT But Faster.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Token Merging: Your ViT But Faster
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.606124Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cd564c9-5191-458a-aedd-52c0215a2c01 · outbound
This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.
DyCoke: Dynamic Compression of Tokens for Fast 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 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.613617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2a99899-602b-4928-917b-a694295f98bc · outbound
This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.616706Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df522aa3-0ead-41ab-be2a-79ddb14ba327 · outbound
This paper cites MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.620060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95365fbd-939e-4e5a-a890-886f386ae174 · outbound
This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.623746Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 662dffc3-0195-443e-ad69-8d197f7c7c51 · outbound
This paper cites an unresolved cited work.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T14:40:24.201372Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e3850772-27f2-49c4-a1e0-a3a152f19c32 · outbound
This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.629903Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8b7dab3-7667-4bb2-91bf-6d44d6c44b0b · outbound
This paper cites LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.633017Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b194b244-12ef-4680-adde-3143b57ddb2f · outbound
This paper cites Mini-internvl: a flexible-transfer pocket multi-modal model with 5% parameters and 90% perfor- mance.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Mini-internvl: a flexible-transfer pocket multi-modal model with 5% parameters and 90% perfor- mance
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.194332Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation bbf33c42-8533-40eb-b11c-1c4948d21924 · outbound
This paper cites Masked autoencoders are scalable vision learners.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Masked autoencoders are scalable vision learners
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.186675Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 56211308-d450-46b8-92cd-3d234d3530b8 · outbound
This paper cites Lita: Language instructed temporal-localization assistant.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Lita: Language instructed temporal-localization assistant
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.178893Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6bf8a6d5-43ad-4ec1-b6b1-ed857fabb90f · outbound
This paper cites An empirical study of llama3 quan- tization: From llms to mllms.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models An empirical study of llama3 quan- tization: From llms to mllms
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.170570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0d8fc5da-66ec-44b0-9c2a-62c868714354 · outbound
This paper cites Phi-2: The surprising power of small language models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Phi-2: The surprising power of small language models
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.162483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8c8faeba-6d76-4ed4-aa97-f43027f3e992 · outbound
This paper cites Effec- tiveness assessment of recent large vision-language models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Effec- tiveness assessment of recent large vision-language models
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.155676Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 890ac9fe-8c70-4b02-8a4b-12d0d1fe1eac · outbound
This paper cites Chat-univi: Unified visual representation em- powers large language models with image and video under- standing.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Chat-univi: Unified visual representation em- powers large language models with image and video under- standing
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.148286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 80b32cc2-0d2b-4c0f-8c76-96ca4d5939a0 · outbound
This paper cites Lmms-eval: Accelerating the development of large multimodal models, 2024.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Lmms-eval: Accelerating the development of large multimodal models, 2024
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.656184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 444d4a0e-ab21-4579-958c-ccb442e8d808 · outbound
This paper cites LLaVA-OneVision: Easy Visual Task Transfer.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models LLaVA-OneVision: Easy Visual Task Transfer
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.659409Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aeb20722-42e1-4cb7-b13f-c73494ca640e · outbound
This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.662070Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4ca789b6-071b-4145-ba0d-ae457bde8cca · outbound
This paper cites Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.137189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation cca5709e-d411-4a1c-baff-a9270c33971d · outbound
This paper cites Tp2o: Creative text pair-to-object generation using balance swap-sampling.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Tp2o: Creative text pair-to-object generation using balance swap-sampling
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.128620Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ad9317d3-9ab5-4df5-877d-82cced281e69 · outbound
This paper cites VideoChat: Chat-Centric Video Understanding.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models VideoChat: Chat-Centric Video Understanding
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.670848Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3ac6aed7-a5d3-4faa-b167-7b296074fdfe · outbound
This paper cites Mvbench: A comprehensive multi-modal video understand- ing benchmark.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Mvbench: A comprehensive multi-modal video understand- ing benchmark
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.121356Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 98ff61bf-30bd-421d-8bda-b5463da11204 · outbound
This paper cites Llama-vid: An image is worth 2 tokens in large language models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Llama-vid: An image is worth 2 tokens in large language models
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.114221Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 686683fb-6050-47cf-a523-1f7a04717388 · outbound
This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.680826Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40330da5-7f79-4122-a3dc-ed1e6da79230 · outbound
This paper cites MoE-LLaVA: Mixture of Experts for Large Vision-Language Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.684059Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d988134-9f0d-49c4-acc3-8016818a5067 · outbound
This paper cites Vila: On pre-training for visual language models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Vila: On pre-training for visual language models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.105739Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a101bd37-0ac1-417c-baa6-8b59d8bce438 · outbound
This paper cites Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.689402Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 80057844-2fee-4228-a585-4e8065661293 · outbound
This paper cites Improved baselines with visual instruction tuning.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Improved baselines with visual instruction tuning
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.692236Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c5f046d1-4fe9-479b-858f-621ffe97f0e4 · outbound
This paper cites Visual instruction tuning.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Visual instruction tuning
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.696074Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e7c4b62-9d33-4e80-aea7-1a1b8a3af018 · outbound
This paper cites Video detail caption, 2024.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video detail caption, 2024
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.092122Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c073fbc5-43d2-4f94-954e-6da67bfaee97 · outbound
This paper cites Valley: Video Assistant with Large Language model Enhanced abilitY.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Valley: Video Assistant with Large Language model Enhanced abilitY
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.701759Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b75e6fbb-1254-4b8a-8ca3-76666289f524 · outbound
This paper cites Gpt-4 model, 2023.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Gpt-4 model, 2023
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.085000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0aba2f3e-02b9-43dc-856b-01242661eed0 · outbound
This paper cites Per- ception test: A diagnostic benchmark for multimodal video models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Per- ception test: A diagnostic benchmark for multimodal video models
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.706916Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0499b5c-2f5d-412a-875a-3c0fa62174d0 · outbound
This paper cites Learning transferable visual models from natural language supervision.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Learning transferable visual models from natural language supervision
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.073626Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 03bae0ac-1fbe-4342-b3e4-9420f2fece5d · outbound
This paper cites TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.713555Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd0dbfeb-3365-4a3a-a75e-4a19c42f8261 · outbound
This paper cites xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.716671Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7118a95f-454d-4822-be9c-bf4500cacae8 · outbound
This paper cites PB-LLM: Partially Binarized Large Language Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models PB-LLM: Partially Binarized Large Language Models
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.719444Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aea40c27-f9b4-47bc-8ff4-03947e4ffb37 · outbound
This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Llava-prumerge: Adaptive token reduction for efficient large multimodal models
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.721994Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3b10fefc-2f69-4e0c-ab17-c914a975ecb5 · outbound
This paper cites TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.724449Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a70519a-1c22-4609-9647-d7ff754b9db5 · outbound
This paper cites Video- mae: Masked autoencoders are data-efficient learners for self-supervised video pre-training.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video- mae: Masked autoencoders are data-efficient learners for self-supervised video pre-training
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.065685Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0a677e7e-f101-400f-b5ad-a44a2a77e18c · outbound
This paper cites LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.730593Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f6822db5-7cbd-4ebd-8023-6aa5e8df054d · outbound
This paper cites Tarsier: Recipes for Training and Evaluating Large Video Description Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Tarsier: Recipes for Training and Evaluating Large Video Description Models
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.734088Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a3bac1f9-6d6d-4692-8fc9-d665278ec2a2 · outbound
This paper cites Small Language Model Meets with Reinforced Vision Vocabulary.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Small Language Model Meets with Reinforced Vision Vocabulary
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.737431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation badc2f20-4a8f-473c-a9a0-017195bb0e1f · outbound
This paper cites Mamballie: Implicit retinex-aware low light enhancement with global-then-local state space.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Mamballie: Implicit retinex-aware low light enhancement with global-then-local state space
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.058338Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 134df1f3-fcb4-491a-adcc-9379af1190e9 · outbound
This paper cites Next-qa: Next phase of question-answering to explaining temporal actions.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Next-qa: Next phase of question-answering to explaining temporal actions
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.049933Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation d607b380-1909-462d-9095-53da1f0b70c4 · outbound
This paper cites Robustmq: benchmarking robustness of quantized models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Robustmq: benchmarking robustness of quantized models
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.040207Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation be08aeb6-a7ee-4f92-bbee-39f6c09fb38e · outbound
This paper cites Novel object synthesis via adaptive text-image harmony.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Novel object synthesis via adaptive text-image harmony
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.030420Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a3ae0252-04b4-478c-b369-08b8ebd2b89b · outbound
This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.749972Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae70fbcb-4bca-4025-b71c-330e23fd0387 · outbound
This paper cites Activitynet-qa: A dataset for understanding complex web videos via question answering.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Activitynet-qa: A dataset for understanding complex web videos via question answering
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.020310Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation fef99eab-0e7f-4355-80be-4bc14eb44e66 · outbound
This paper cites TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.755161Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4d754c0a-2b72-492c-9eec-8d3682e7244c · outbound
This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.757857Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c2d8b2c-e692-45ed-96e0-d939d4fe532c · outbound
This paper cites Lmms- eval: Reality check on the evaluation of large multimodal models, 2024.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Lmms- eval: Reality check on the evaluation of large multimodal models, 2024
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.761430Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 096daa0b-aece-40b1-b582-65cb437d3be2 · outbound
This paper cites TinyLLaVA: A Framework of Small-scale Large Multimodal Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.763783Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cc4c9fcd-7491-4696-ace4-b1513a46cc7c · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T14:40:23.766777Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1056b463-59c5-4538-8142-48d35f621a2f · outbound
This paper cites Llava-phi: Efficient multi-modal assistant with small language model.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models Llava-phi: Efficient multi-modal assistant with small language model
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:24.007353Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 542b4934-4004-4159-bff7-cf40f1ae2ebb · outbound
This paper cites counterfactual reasoning.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models counterfactual reasoning
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T14:40:23.998181Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Pith citing papers
Observation 07f9dd78-b7ea-4ce0-afbc-03b2027df9ca · inbound
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval cites this paper.
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T14:31:40.742289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 3f1acf08-3f3e-4d4d-bf9c-889c2570e0ce · inbound
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models cites this paper.
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:08:09.432264Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f2792e61-63a5-472a-8d51-e05cbbedfa04 · inbound
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding cites this paper.
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T10:56:05.362186Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23f69557-35b7-43b7-9b7c-2d0d26d6a526 · inbound
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs cites this paper.
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T22:24:32.266783Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9fdda23a-e379-4a88-8fda-78e5a5fba147 · inbound
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding cites this paper.
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T20:29:54.595717Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 09cc8165-9107-402e-b976-e1c701189c49 · inbound
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs cites this paper.
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T03:22:01.139852Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 2b08a16f-941a-4a64-8f19-744306d50b72 · inbound
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding cites this paper.
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 2026-08-15T06:32:42.880941+00:00.
Observation 6c70ceb7-65d6-46d6-a34a-39eabd1dee2e · inbound
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding cites this paper.
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T11:31:01.468199Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e3d60966-5cf6-41f8-a06f-eb0f69c2434f · inbound
TTF: Temporal Token Fusion for Efficient Video-Language Model cites this paper.
TTF: Temporal Token Fusion for Efficient Video-Language Model DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T04:06:00.550627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 2dad76de-74ca-4d25-993a-6a3554dad9ed · inbound
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models cites this paper.
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:46:51.549583Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.