Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin | Paper Citation Record

Observation d3fefcc0-c1e5-49a9-8b02-7fb1be112d50 · outbound

This paper cites Qwen2.5-VL Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.184628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bf4cec4-7fbf-4622-8715-6616263e904a · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.189388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6613c666-b789-4a1d-ab34-393cc274f899 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.193471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c552ff0a-8265-45dc-a260-ef63ec3ca58b · outbound

This paper cites ICML , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ICML , year=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.197067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9216dc4a-716e-4300-a6a9-785c5b82ebb1 · outbound

This paper cites ICML , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ICML , year=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.200763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f200349-2f41-498c-bbb6-00669a2110fe · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.204559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 655ff2fc-a489-418d-8f29-ccdc15ad5dab · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.208606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788c189a-8fd3-4e98-b920-0f4319ec14bc · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.211519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36222e3f-701e-4743-b392-5722206979a5 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.214635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa82ddf-0c37-421f-a9fc-9152b55e2ff1 · outbound

This paper cites an unresolved cited work.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.217581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 456cabf5-7ad3-4338-a54b-94098b316d52 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.220359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5433c3-b826-4b3f-8dd8-2695fc491d56 · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.223732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3ed016b-e8d6-4909-8094-f1906e58ba7d · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Gemini: A Family of Highly Capable Multimodal Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.227340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 498c2365-7b92-4d8d-a347-8476b14d3987 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.230915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c95443-0f89-4b8f-b099-9c4efeda70fe · outbound

This paper cites an unresolved cited work.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.234665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04fcfba3-a3aa-4fc8-be22-c34dbc4866f3 · outbound

This paper cites Token Merging: Your ViT But Faster.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Token Merging: Your ViT But Faster

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.237915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daddbc57-a323-435e-9fb5-7d783b1be326 · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.241516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f3ba0b-a1e1-49bf-ac40-98a4e7670049 · outbound

This paper cites arXiv preprint arXiv:2403.15388 , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin arXiv preprint arXiv:2403.15388 , year=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.244923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd2cbfe-3851-4f2f-9a68-ff4bc8485b30 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.248316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2530b53-5a83-4dd9-9946-b4b97b816b33 · outbound

This paper cites MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.251891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c74d0f9-56b4-442e-91c8-51e2e8a3ec73 · outbound

This paper cites TokenPacker: Efficient Visual Projector for Multimodal LLM.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.255625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c9d12e3-3039-410b-b995-177db0a4e534 · outbound

This paper cites arXiv preprint arXiv:2411.17686 , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin arXiv preprint arXiv:2411.17686 , year=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.259308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05b1e3c-ad65-4f76-a39e-be00825a9b60 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.263104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fd6f05-f54a-4edf-a71b-92ff8ec78783 · outbound

This paper cites Qwen Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.266859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ed976d5-52fa-4f87-b350-6d6483148a3a · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.270569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100f7f4a-5ab0-4897-aeac-f15ce15c3ddc · outbound

This paper cites LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.274367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51982df7-5667-4d16-8a10-81e67ee8acb4 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.278391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc6395f-69e3-4fb0-b1e5-d9efa37ef0cf · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.281720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6164b773-31a9-42e1-a6bc-7d14aa21dccc · outbound

This paper cites Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.285282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e270aa12-acc4-49a4-8290-05c05ff6845a · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.288837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b888b749-faa7-4be3-b08e-3024b0e967d0 · outbound

This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.292670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f172363-a22b-4c8d-b29a-583864f922bb · outbound

This paper cites ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.296106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e6a82c-d1ad-4b30-9c0c-272f3de478b9 · outbound

This paper cites Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.299362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608d509a-bded-40cb-8ee1-8cb0781c9a7d · outbound

This paper cites InternLM2 Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin InternLM2 Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.302724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b9e655-b4f4-4e0a-9a03-f79c0a52089d · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.305742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa4e496-0e8a-42c7-b286-2b822f85099c · outbound

This paper cites WACV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin WACV , year=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.308686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb99119-9302-4632-ba03-ef4f6964d551 · outbound

This paper cites WACV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin WACV , year=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.312135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678ccdbd-6575-4c75-9c72-c3410921ded0 · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.315460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9567cdd9-78a5-40e5-b775-3c853645e88b · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.319438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8060f9d7-21bd-49d3-b775-04767abd0b3a · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.322726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9bd4578-b93d-4a31-a85d-2ccab01855f4 · outbound

This paper cites EMNLP , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin EMNLP , year=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.326019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27495724-e151-41ce-b800-bc8f69d17a57 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.329346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c74206c-3482-49aa-93da-85f0681ee83f · outbound

This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.332660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b16f436-314e-4cb7-879a-1c7375f87e85 · outbound

This paper cites ECCV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ECCV , year=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.336324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8e980ba-49ac-46a2-9ef9-9724a899f10d · outbound

This paper cites arXiv e-prints , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin arXiv e-prints , year=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.339687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc095e69-dfcf-4ff8-96bd-0af283339d9e · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.343274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d44975fa-5d17-40c0-a7a4-11d836af12bf · outbound

This paper cites mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.347023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a18acc9-376b-4343-b92c-c026baf70eed · outbound

This paper cites Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.350680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20e53230-899e-417f-92db-a8dfd19d0703 · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.354396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d406f4c0-480d-4dd0-8802-74a953a56716 · outbound

This paper cites ECCV , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ECCV , pages=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.357716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef15e32c-ce71-4f94-aa36-064ccacaabc5 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.360982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ef600a-d58c-4cbe-8cdb-1238e205f75b · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.364525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bbe1032-10e0-43e0-96f6-cb7127e9fa02 · outbound

This paper cites Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.367925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57db35f6-fe3e-49e7-a9fd-989fbf4a5cde · outbound

This paper cites TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

Reference 54

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T04:30:15.167292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c4bfe39b-061b-4146-86c4-abc0b20949bd · outbound

This paper cites FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.375574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72812fb3-2681-4c41-b044-677deb2ad573 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.379313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7c065a8-5ccc-4a65-a1a6-4ab6c37f6b8f · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.382832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19a85498-d981-42e3-8a41-06ba36b4a12c · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.386155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868f1a82-2656-424b-b0a5-40c2d9dde5d3 · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.856172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 709f01b0-9b09-40de-bf1b-d9a8590fbc55 · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.393401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 444a931e-74ea-4114-b2aa-e45f19f5938f · outbound

This paper cites ICML , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ICML , pages=

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.845287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d3efd223-49a3-4e6d-b047-506a4b0bddac · outbound

This paper cites DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.399358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 035b1fdb-dc96-40b6-aa2e-e4ddf1c81ea2 · outbound

This paper cites ACM Transactions on Database Systems (TODS) , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ACM Transactions on Database Systems (TODS) , pages=

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.834253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6adf513c-42ee-4652-8ca4-90b192613326 · outbound

This paper cites GPT-4o System Card.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin GPT-4o System Card

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.406724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8db08b1-f786-44c5-981b-5861db570550 · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.409858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d548e17-b98a-459e-b572-53109317b777 · outbound

This paper cites Proceedings of the 32nd ACM International Conference on Multimedia , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Proceedings of the 32nd ACM International Conference on Multimedia , pages=

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.414203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4717ca4d-4ce6-4747-b553-94e6f052838b · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.417640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d630164-4544-449e-8ca2-cd2eb7387854 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.421428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc0c6ba-b6c3-4fb4-a600-100a0fafb2da · outbound

This paper cites ECCV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ECCV , year=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.424914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db8c182a-0f84-47e2-98b8-c2c81904cb62 · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.800164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 457f16e9-e01a-42bd-a39e-d79d004b12fc · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.432345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e148b1e9-b912-4325-bbd0-0e0adafa7149 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.436166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4ca747-1fac-483b-b8cc-40afb9b37933 · outbound

This paper cites ICCV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ICCV , year=

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.788679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 289f2c93-275c-42ca-99dd-849180301cb3 · outbound

This paper cites Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.443529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7414c56-1099-4ff0-8fe4-97423e1612eb · outbound

This paper cites Qwen3-VL Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen3-VL Technical Report

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.447236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ee7d7b-0e4d-426e-92b7-98060254abd8 · outbound

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

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin LLaVA-OneVision: Easy Visual Task Transfer

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.450759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c5c2e7-9d73-4d01-9880-688927c997e7 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.775868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b7787d07-583c-4a18-81f7-f54d3e940750 · outbound

This paper cites AAAI , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin AAAI , year=

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.765249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3ec38fa5-dacd-434a-b02d-69faf847e68e · outbound

This paper cites ECCV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ECCV , year=

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.754472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 40a305b0-f104-48b5-866b-d91e4a27bc00 · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.743459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f66abced-ddcb-4954-8520-3e15de978fef · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.731968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation caa523ce-41c7-476e-a371-1ba415be5e77 · outbound

This paper cites Seed1.5-VL Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Seed1.5-VL Technical Report

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.471570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e278458-c443-4484-aac3-85b23c675074 · outbound

This paper cites InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.475211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3da428c-2a7a-49f5-ad92-2ef1b917e3e8 · outbound

This paper cites NeurIPS , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin NeurIPS , year=

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.478903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33aaf4d2-def7-4a77-8995-12df540f570b · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin LLaMA: Open and Efficient Foundation Language Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.482592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 019cdcc6-3c79-4eb6-aa13-02a89bf8fe65 · outbound

This paper cites DeepSeek-V3 Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin DeepSeek-V3 Technical Report

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.486359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9fe5aea-29c6-4dcd-8398-07cc5861b1cb · outbound

This paper cites Qwen3 Technical Report.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Qwen3 Technical Report

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.490105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d21e384-dc0c-4128-b777-d704c90f14bb · outbound

This paper cites AAAI , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin AAAI , year=

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.712087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 044e74ac-68f1-45b6-b553-57d2505b46b7 · outbound

This paper cites ECCV , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin ECCV , year=

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.497187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c659c3-613d-410a-a1eb-09ec16f00ad9 · outbound

This paper cites CVPR , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin CVPR , year=

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.500265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c403b17c-df75-49e6-a8f4-2bb4ad3f6767 · outbound

This paper cites SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.503529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ec82576-f1d4-4563-a1ce-99ee577f7eab · outbound

This paper cites SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.506806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 204158c3-e71a-4351-8031-9963114faf95 · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.510251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41a5184a-a68f-454e-a9cd-4422249b0d01 · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.686593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 09aec212-b394-4a0a-ab5a-ec21b1b564b9 · outbound

This paper cites OneThinker: All-in-one Reasoning Model for Image and Video.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin OneThinker: All-in-one Reasoning Model for Image and Video

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.517712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8dbd646-f81e-45ae-9aed-dae7da1668b8 · outbound

This paper cites LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.521293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d1790a-cddf-444e-b41d-4f6533f24bba · outbound

This paper cites arXiv preprint arXiv:2601.22674 , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin arXiv preprint arXiv:2601.22674 , year=

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.525086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b0d891-b32c-481b-b396-e3e10cc6872e · outbound

This paper cites AAAI , pages=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin AAAI , pages=

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.675107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 13f1b919-3589-4789-9d9a-62e60ffdf5f7 · outbound

This paper cites Findings of the Association for Computational Linguistics: NAACL 2025 , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin Findings of the Association for Computational Linguistics: NAACL 2025 , year=

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:30:15.662753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f250d59f-7c12-45d5-ac2b-c74a27ad96b2 · outbound

This paper cites arXiv preprint arXiv:2602.23699 , year=.

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin arXiv preprint arXiv:2602.23699 , year=

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-10T04:30:14.535753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers