FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression | Paper Citation Record

Observation b8a476c1-9b94-4994-8048-469c0fea17c3 · outbound

This paper cites GPT-4 Technical Report.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.227561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 630a6798-b520-4f35-bebb-085cdcd1846f · outbound

This paper cites Bottom-up and top-down attention for image captioning and visual question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Bottom-up and top-down attention for image captioning and visual question answering

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.231500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7153172c-ea37-4214-8c96-4f76675d4715 · outbound

This paper cites Qwen Technical Report.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.234380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bbea82d-0bf0-4f1b-98f7-05fb89259d53 · outbound

This paper cites Gemma: Introducing new state-of-the-art open models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Gemma: Introducing new state-of-the-art open models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.237958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48487edc-c0c6-4e0c-9400-a6d7a23f3fca · outbound

This paper cites Language models are few-shot learners.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Language models are few-shot learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.240691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997d8738-1bd1-4fd5-9852-7e9055b7c5f3 · outbound

This paper cites Honeybee: Locality-enhanced projector for multimodal llm.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Honeybee: Locality-enhanced projector for multimodal llm

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.243430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5ce3a98-1b80-4e69-8f83-431aa4261138 · outbound

This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.246133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2f7a125-3085-4c86-8b39-27d816b7fb04 · outbound

This paper cites Lawrence Zit- nick.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Lawrence Zit- nick

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.249780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25bd50ef-cdc9-4fcf-95db-4c4bdd09e788 · outbound

This paper cites PaLI: A Jointly-Scaled Multilingual Language-Image Model.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression PaLI: A Jointly-Scaled Multilingual Language-Image Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.252944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da9f6f9-2f64-4a7e-bc1e-72e72a807aee · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open- source suites, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression How far are we to gpt-4v? closing the gap to commercial multimodal models with open- source suites, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.256084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dffd154-db90-4c29-a3ad-c7e60474eb54 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.258655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cfabdcd-b567-4d75-9956-05574f714485 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.261489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9544fdc1-b620-420f-9a3f-199c7d42de2d · outbound

This paper cites Instructblip: Towards general- purpose vision-language models with instruction tuning,.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Instructblip: Towards general- purpose vision-language models with instruction tuning,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.264453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402e63c1-ce06-472d-b65b-62a8131ba07d · outbound

This paper cites Mme: A compre- 9 hensive evaluation benchmark for multimodal large language models, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mme: A compre- 9 hensive evaluation benchmark for multimodal large language models, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:09.007536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2e3c46bf-2041-457c-a0a3-71607bc6ddfc · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:09.000272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 527398e0-0bf9-48a6-a377-b88a7d565e53 · outbound

This paper cites Minicpm: Un- veiling the potential of small language models with scalable training strategies, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Minicpm: Un- veiling the potential of small language models with scalable training strategies, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.992917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eab121c9-2d36-4c35-a170-f3587b65e6eb · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.275372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0c000c-631d-492c-97a2-2c3ead4dec59 · outbound

This paper cites Token merging for training- free semantic binding in text-to-image synthesis, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Token merging for training- free semantic binding in text-to-image synthesis, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.985333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dc1890a4-bb9d-4e1a-bc26-0cbe64f298a1 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.977404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e149fc0b-b43f-464a-b106-f780aadeb0cb · outbound

This paper cites Phi-2: The surprising power of small language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Phi-2: The surprising power of small language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.969681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5200a819-4edd-424e-bdc8-2efbd06283bb · outbound

This paper cites In defense of grid features for visual question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression In defense of grid features for visual question answering

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.962265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2f69eca5-7024-437d-b957-f3d20f9fb4be · outbound

This paper cites Contrast and classify: Training robust vqa models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Contrast and classify: Training robust vqa models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.955006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 295cde2f-b1d4-433a-9d22-a4aa1aad5b48 · outbound

This paper cites Referitgame: Referring to objects in pho- tographs of natural scenes.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Referitgame: Referring to objects in pho- tographs of natural scenes

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.947365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 14175937-1d25-4def-9bdb-51590fdf9c75 · outbound

This paper cites A diagram is worth a dozen images.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression A diagram is worth a dozen images

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.293615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19186a00-6f9d-426d-a3ce-03d6c2c877e0 · outbound

This paper cites Seed-bench: Bench- marking multimodal large language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Seed-bench: Bench- marking multimodal large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.936399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6fb39a02-0e10-4c36-befe-608ae9bd53d9 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.299006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f294ee1a-9caf-4144-95ce-b22068d88a12 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.301741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3339ae5-77eb-42b9-97b5-e22a2112aad6 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.924912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 64483dff-5527-4c2b-ba48-8dfb8a2a7b10 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.306619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0e2b9f2-4dee-4358-9153-54d800348272 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Evaluating object hallucination in large vision-language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.917574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation be65e829-2862-4674-a628-60aeec5efeb0 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.311714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec3cd88-490d-46c8-b9b7-102a66d57b8f · outbound

This paper cites Mon- key: Image resolution and text label are important things for large multi-modal models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mon- key: Image resolution and text label are important things for large multi-modal models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.909721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1a3aeb31-8b46-455b-aa92-cc18366b8b84 · outbound

This paper cites Improved baselines with visual instruction tuning.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Improved baselines with visual instruction tuning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.902388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e5c29df2-6b30-4368-b898-6e8415d2ca4f · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.894198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b77bb695-f88d-4844-aa9e-2d08401f8d9f · outbound

This paper cites Visual instruction tuning.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Visual instruction tuning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.885784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8e6abf79-d0d5-4d55-a27f-6f3591ac9396 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mmbench: Is your multi-modal model an all-around player?, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.877386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4effb140-fbb8-4d2c-943c-6b91af32192d · outbound

This paper cites Decoupled Weight Decay Regularization.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Decoupled Weight Decay Regularization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.326784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d39eb5-e572-43be-ad1b-f553186cd52e · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.329705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab43a5b8-737a-4264-a66a-835219ebd03b · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.332592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c5abab-e79f-4606-9c23-25d0eb12da07 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.335366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7327ee58-e4d1-4ef8-ac14-950aa62dff77 · outbound

This paper cites To- wards lightweight transformer via group-wise transforma- tion for vision-and-language tasks.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression To- wards lightweight transformer via group-wise transforma- tion for vision-and-language tasks

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.865032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f496d380-de84-48cd-9559-242a5d46327a · outbound

This paper cites Cheap and quick: Efficient vision- language instruction tuning for large language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Cheap and quick: Efficient vision- language instruction tuning for large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.857341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f99125b1-42d1-4b03-b293-14644c5b97a5 · outbound

This paper cites Moil: Momentum imita- tion learning for efficient vision-language adaptation.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Moil: Momentum imita- tion learning for efficient vision-language adaptation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.343738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9fbdc75-f9fc-4890-b09e-5eb04d28568a · outbound

This paper cites Towards language-guided visual recog- nition via dynamic convolutions.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Towards language-guided visual recog- nition via dynamic convolutions

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.845990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a0e638c8-4f5a-4ed1-ba4a-15faa67b0baf · outbound

This paper cites Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.348453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e27a5ca-7e74-46f2-ae78-61ad377c1b7f · outbound

This paper cites Chartqa: A benchmark for question answer- ing about charts with visual and logical reasoning, 2022.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Chartqa: A benchmark for question answer- ing about charts with visual and logical reasoning, 2022

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.838006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b94b76ec-e7bd-4786-92b9-4028b6f44007 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.829927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0cc2e6e6-aab0-40db-b992-db6c012216f2 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression DINOv2: Learning Robust Visual Features without Supervision

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.356012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 208567de-d3f6-45da-9e74-a99002bd76a9 · outbound

This paper cites Learning transferable visual models from natural language supervision, 2021.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Learning transferable visual models from natural language supervision, 2021

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.358592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54f0555-8992-441c-8355-7a9e7a0297b2 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Learning transferable visual models from natural language supervi- sion

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.361676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09e7d82-b271-4736-aea6-4599f8fcc571 · outbound

This paper cites Imp: Highly Capable Large Multimodal Models for Mobile Devices.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Imp: Highly Capable Large Multimodal Models for Mobile Devices

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.364232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 873ba2fe-e190-4711-860f-6bf6827ed107 · outbound

This paper cites When do we not need larger vision models?, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression When do we not need larger vision models?, 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.812922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 16054fb2-0a0c-4f1b-8662-43a7cd5815a4 · outbound

This paper cites Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.369438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60bbf9ad-f9a3-4482-b029-b3826a42ba27 · outbound

This paper cites Towards vqa models that can read.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Towards vqa models that can read

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.805615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 32e1e7cc-c75c-48c7-bf92-4d50e1954a75 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Gemma: Open Models Based on Gemini Research and Technology

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.374548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d80c96-c396-4a7f-8abc-a8b4742a2691 · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.377247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2dddbc-3ab3-413d-bbb2-889b9be9d0df · outbound

This paper cites Well-Read Students Learn Better: On the Importance of Pre-training Compact Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.379783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4b708de-7375-4531-97d7-9e73da4f9c3e · outbound

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.382822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f271e797-ccf5-484f-8716-5a434963d2a9 · outbound

This paper cites Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.385543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df808884-647b-4e16-bd72-646e0931afae · outbound

This paper cites Stacked attention networks for image question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Stacked attention networks for image question answering

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.798043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2bf59c01-1ee7-41e3-ad7f-a02e7a9590f1 · outbound

This paper cites mplug-owl: Modularization empowers large language mod- els with multimodality, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression mplug-owl: Modularization empowers large language mod- els with multimodality, 2024

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.790234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 55a8b314-8652-4f49-8c5e-a1fc978e722e · outbound

This paper cites Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.393098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f936f9-cd1b-4c9a-9078-69b019d9c7ef · outbound

This paper cites Mm-vet: Evaluating large multimodal models for integrated capabilities, 2023.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mm-vet: Evaluating large multimodal models for integrated capabilities, 2023

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.782501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a8ab1367-712e-4e3e-ab80-7da9fa0e8e85 · outbound

This paper cites Deep modular co-attention networks for visual question an- swering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Deep modular co-attention networks for visual question an- swering

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.775215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f72e0beb-c44f-48c2-96de-368aa8556536 · outbound

This paper cites Tinygpt-v: Efficient multimodal large lan- guage model via small backbones, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Tinygpt-v: Efficient multimodal large lan- guage model via small backbones, 2024

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.767930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation caa8085a-2a3c-4a56-a9cc-ff0e030ee692 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understand- ing and reasoning benchmark for expert agi.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mmmu: A massive multi-discipline multimodal understand- ing and reasoning benchmark for expert agi

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.760040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b2f69a39-5f6d-4fe1-94ea-6661d0005158 · outbound

This paper cites Sigmoid loss for language image pre-training,.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Sigmoid loss for language image pre-training,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.407076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acf37657-d8f1-4fec-a07d-c07e8a932943 · outbound

This paper cites MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.409547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f53947-2e19-437d-93ad-4e44cb06403e · outbound

This paper cites Lmms- eval: Reality check on the evaluation of large multimodal models, 2024.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Lmms- eval: Reality check on the evaluation of large multimodal models, 2024

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.412907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c07de0f-ffba-412b-b950-8ba9bbd313f2 · outbound

This paper cites Vinvl: Revisiting visual representations in vision-language models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Vinvl: Revisiting visual representations in vision-language models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.415267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4536e021-a980-4ee2-8a99-b48b30bccffe · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression OPT: Open Pre-trained Transformer Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.417720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd6a1d4-33c7-4ec0-94cd-52a422597aae · outbound

This paper cites Free vqa models from knowledge iner- tia by pairwise inconformity learning.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Free vqa models from knowledge iner- tia by pairwise inconformity learning

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.740215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 39a79b3a-3f8d-4519-9f6c-dfb5d8b3ebd6 · outbound

This paper cites Trar: Routing the attention spans in transformer for visual question answering.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Trar: Routing the attention spans in transformer for visual question answering

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.732876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 863d176b-39ce-4965-b82c-bc35082c741d · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models, 2023.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Minigpt-4: Enhancing vision-language understanding with advanced large language models, 2023

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.725697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d31a72e-f5cf-467c-bda0-e859e0ea21ac · outbound

This paper cites Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T21:37:08.427822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1cb42e-0145-42bc-93d2-d71b52a7757a · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.718218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 044164c0-8c90-40f7-8768-cc4f0c7ebb24 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.711080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9803d311-a481-4c98-9916-a256a7ef60a0 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.702909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b8c945af-388a-4435-8980-7a542ac4e4a4 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.695244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e7484725-fc2b-4fdf-8647-f81f95fc8b3c · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.686740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5d5ce4cc-e1d8-4f57-97bb-d4ec7709e76a · outbound

This paper cites Therefore, the value of the square in the figure is 2.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Therefore, the value of the square in the figure is 2

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.679023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 823a836a-6e37-43b4-bf38-f2db8912ba61 · outbound

This paper cites control center.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression control center

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.670988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3ab4ddba-1331-4c01-9e1b-b3940d8881e0 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 84

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.655902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ad67f5a0-d0b2-4b9b-95da-b78400b582a0 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 85

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.648609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 275209cb-2bf7-4178-aac4-6d48a670f5a5 · outbound

This paper cites an unresolved cited work.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:37:08.641489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9c492150-ab38-4202-8025-e9e1cf4e7473 · outbound

This paper cites RIGHT",.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression RIGHT",

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.633594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6c5fd70e-35c4-484c-aaea-fffc2a260bd9 · outbound

This paper cites Decreased.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression Decreased

Reference 2012

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:37:08.663257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers