OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models | Paper Citation Record

Observation 321e6400-3136-4806-92de-a7d1d23f542e · outbound

This paper cites Token Merging: Your ViT But Faster.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Token Merging: Your ViT But Faster

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.403845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f66cb5-7bf5-47f5-ba9c-fdd856498ff2 · outbound

This paper cites Animageisworth1/2tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Animageisworth1/2tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.407268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d09a710-17d7-4815-991c-d667f60a561b · outbound

This paper cites Howfararewetogpt-4v? closingthegaptocommercialmultimodalmodelswithopen-sourcesuites.ScienceChina Information Sciences, 67(12):220101, 2024.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Howfararewetogpt-4v? closingthegaptocommercialmultimodalmodelswithopen-sourcesuites.ScienceChina Information Sciences, 67(12):220101, 2024

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.409945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9de0de9-3c6d-481f-834f-0342e2aa925e · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Instructblip: Towards general-purpose vision-language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.412497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff12260-6c83-4bfa-aff2-95f38fdb89ff · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.414925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd625f2-1585-45a4-825d-d7a855029a5d · outbound

This paper cites OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.417708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b3b869-dc30-467d-8c87-279cf1c3c586 · outbound

This paper cites Study on density peaks clustering based on k-nearest neighbors and principal component analysis.Knowledge-Based Systems, 99:135–145, 2016.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Study on density peaks clustering based on k-nearest neighbors and principal component analysis.Knowledge-Based Systems, 99:135–145, 2016

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.420658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4de105d5-329a-4524-a97d-03d201a4c5bc · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.422877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 059812d1-8ab1-4999-9197-160ea2f0323d · outbound

This paper cites Video-mme: Thefirst-evercomprehensiveevaluationbenchmarkofmulti-modalllmsinvideoanalysis.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Video-mme: Thefirst-evercomprehensiveevaluationbenchmarkofmulti-modalllmsinvideoanalysis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.425121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfdb2d56-db0f-4f24-bc84-22ffd3c0f001 · outbound

This paper cites VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.427425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc2347b-b2c4-413b-98e5-97eddb1c6c81 · outbound

This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.430169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5cc7892-3b71-4048-9417-80df2d7bb9ac · outbound

This paper cites Prunevid: Visualtokenpruningforefficientvideolargelanguagemodels.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Prunevid: Visualtokenpruningforefficientvideolargelanguagemodels

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.432700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9109553f-81e9-41e3-b035-1c8b65ce404d · outbound

This paper cites GPT-4o System Card.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models GPT-4o System Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.434801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15f6d9a0-23c7-41ca-aebf-0b81797b5571 · outbound

This paper cites Efficient multimodal large language models: A survey.Visual Intelligence, 3(1):27, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Efficient multimodal large language models: A survey.Visual Intelligence, 3(1):27, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.437064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f2fadfb-0fbd-453b-b8eb-523d0aa91ac5 · outbound

This paper cites Tokenpruninginaudiotransformers: Optimizingperformanceanddecodingpatchimportance.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Tokenpruninginaudiotransformers: Optimizingperformanceanddecodingpatchimportance

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.439280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9abbf839-5c61-43e4-b63c-45e52ad589eb · outbound

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

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.441373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1da3b83-dd4a-4444-bab5-dd0b8794c78d · outbound

This paper cites Omnivideobench: Towards audio-visual understanding evaluation for omni mllms.arXiv preprint arXiv:2510.10689, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Omnivideobench: Towards audio-visual understanding evaluation for omni mllms.arXiv preprint arXiv:2510.10689, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.443570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4a87ba-6e4e-4cfb-8dd4-4b94e61d93cd · outbound

This paper cites Accelerating Transducers through Adjacent Token Merging.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Accelerating Transducers through Adjacent Token Merging

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.445710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84198396-a7f8-490a-8c42-3d7f356f78eb · outbound

This paper cites Video-llava: Learningunitedvisualrepresentation by alignment before projection.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Video-llava: Learningunitedvisualrepresentation by alignment before projection

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.448375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc2ff65-e3aa-4421-a9f2-7a88e5ea5509 · outbound

This paper cites Speechprune: Context-awaretokenpruningforspeechinformationretrieval.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Speechprune: Context-awaretokenpruningforspeechinformationretrieval

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.450552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16458f34-6e67-4409-b267-c34321a208ce · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.452730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002db1f9-8ec1-4c54-8963-c763ae79e93c · outbound

This paper cites Javisgpt: A unified multi-modal llm for sounding-video comprehension and generation.arXiv preprint arXiv:2512.22905, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Javisgpt: A unified multi-modal llm for sounding-video comprehension and generation.arXiv preprint arXiv:2512.22905, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.455019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d987d6-eb0f-4b9c-94fe-1528559f14d7 · outbound

This paper cites Quota: Query-orientedtokenassignmentviacotquerydecoupleforlongvideocomprehension.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Quota: Query-orientedtokenassignmentviacotquerydecoupleforlongvideocomprehension

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.457179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f7c4df-4658-4ab2-a502-5c223a79f474 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.459406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fdf5772-7ece-4cb8-9b19-6f222f231419 · outbound

This paper cites Ompq: Orthogonalmixedprecisionquantization.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Ompq: Orthogonalmixedprecisionquantization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.461676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f66ed9-9459-48ff-b97a-2420bd797493 · outbound

This paper cites Affinequant: Affine transformation quantization for large language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Affinequant: Affine transformation quantization for large language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.463908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dc8079b-e33c-4b4b-b4da-c8c00ba098c9 · outbound

This paper cites Norm of word embedding encodes information gain.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Norm of word embedding encodes information gain

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.466408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0977b41-472a-41a4-960c-2fa59eb9fb87 · outbound

This paper cites Prentice-Hall, Inc., 1993.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Prentice-Hall, Inc., 1993

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.468638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f6cacd-4bba-4e32-95a1-0fe2c33d9367 · outbound

This paper cites Learning transferable visual models from natural language supervision.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Learning transferable visual models from natural language supervision

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.470907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45082798-ef54-40bc-a8c1-fd0ebd7be22d · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient largemultimodalmodels.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Llava-prumerge: Adaptive token reduction for efficient largemultimodalmodels

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.473156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f4436a-e2e2-4915-9584-7b39520743f4 · outbound

This paper cites Holitom: Holistictokenmergingforfastvideolarge language models.arXiv preprint arXiv:2505.21334, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Holitom: Holistictokenmergingforfastvideolarge language models.arXiv preprint arXiv:2505.21334, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.475377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13f7504-37f7-471b-9130-247bf434fc4f · outbound

This paper cites Whentokenstalktoomuch: Asurveyofmultimodallong-contexttokencompressionacrossimages,videos,andaudios.arXiv preprint arXiv:2507.20198, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Whentokenstalktoomuch: Asurveyofmultimodallong-contexttokencompressionacrossimages,videos,andaudios.arXiv preprint arXiv:2507.20198, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.477789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202b797a-e3db-4576-8b2a-c09a7bd4aafe · outbound

This paper cites Less is more: A simple yet effective token reduction method for efficient multi-modal llms, 2024.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Less is more: A simple yet effective token reduction method for efficient multi-modal llms, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.480165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9942ec5b-7557-407f-b7d9-2993050d133e · outbound

This paper cites video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.482439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cb3ad99-2e98-4a33-883d-366a444027cb · outbound

This paper cites Lvpruning: Aneffectiveyet simple language-guided vision token pruning approach for multi-modal large language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Lvpruning: Aneffectiveyet simple language-guided vision token pruning approach for multi-modal large language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.485107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389089a4-dba0-4775-9416-aeb0594fe69c · outbound

This paper cites video-salmonn2: Caption-enhanced audio-visual large language models.arXiv preprint arXiv:2506.15220, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models video-salmonn2: Caption-enhanced audio-visual large language models.arXiv preprint arXiv:2506.15220, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.487469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1abf4e1-5c5e-419c-b352-268351089ee5 · outbound

This paper cites Dycoke: Dynamic compression of tokens for fast video large language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Dycoke: Dynamic compression of tokens for fast video large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.489634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f3f3d0-320c-447f-b65e-a8f897e7220e · outbound

This paper cites OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.491885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d90096e6-6bc9-4058-8128-d9105b6d4946 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.494236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d68d8d24-61c0-471f-8d6a-fa0e68d8048d · outbound

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

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.496554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 150dbaaf-1f2a-4d27-9ad0-b56e483c3e4e · outbound

This paper cites Longvlm: Efficientlongvideounderstandingvia large language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Longvlm: Efficientlongvideounderstandingvia large language models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.499048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a297e47-a33d-4b46-b9ba-98aefa4dca7b · outbound

This paper cites Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.501212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f0b1861-64ad-44e0-814a-c39585874b8d · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.503571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84d5c24-21e8-461e-969a-542e51c30061 · outbound

This paper cites Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.505966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a881aeeb-654d-41b9-aa74-bd3ab75d9706 · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.508465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2813c016-831d-41fa-9431-b84d010c32e4 · outbound

This paper cites Qwen2.5-Omni Technical Report.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Qwen2.5-Omni Technical Report

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.510858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41fde0e2-583f-4cd2-8245-5a01599fd579 · outbound

This paper cites Qwen3-Omni Technical Report.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Qwen3-Omni Technical Report

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.513476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bcccdc2-9feb-42fb-acce-f629ddb82464 · outbound

This paper cites HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.515743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb89aad-2a96-41af-aa93-e67ca05fd351 · outbound

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

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Visionzip: Longer is better but not necessary in vision language models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.518149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bbef8c0-7495-4973-9d00-73a4a76939eb · outbound

This paper cites Omnivinci: Enhancing architecture and data for omni-modal understanding llm.arXiv preprint arXiv:2510.15870, 2025.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Omnivinci: Enhancing architecture and data for omni-modal understanding llm.arXiv preprint arXiv:2510.15870, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.520291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd4ec0f3-2ddf-4830-b903-7a0a7a708e1a · outbound

This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.522646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89bf6c89-a6a6-480f-ade9-e192819a8638 · outbound

This paper cites R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.524979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f42ee904-aff0-419d-9760-a9309a7dff18 · outbound

This paper cites An Information Theory-inspired Strategy for Automatic Network Pruning.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models An Information Theory-inspired Strategy for Automatic Network Pruning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.527486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa2f2caa-5eee-46f6-b717-7e92b3b2fa4c · outbound

This paper cites Self-Embed.

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Self-Embed

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T04:02:54.529833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers