MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning | Paper Citation Record

Observation 3509e6fe-17cc-4f38-a96f-c7bc8453f957 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:14.734761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4107bf47-e436-4f5c-8fd6-bd4191b4c2f1 · outbound

This paper cites write newline.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:14.860484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f2ad7b1-59c7-4c4d-a721-e5c1dc70fc6b · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:15.006639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8354bbe4-7984-416d-96f8-b20b65d1236e · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.241059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 997a9521-839a-4566-9bda-ddc669f88f25 · outbound

This paper cites PaLM 2 Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning PaLM 2 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:15.392288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d73ddc-ad49-4d92-a802-17d5dcb5f9c6 · outbound

This paper cites Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:15.587037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d220843a-790f-4b94-93b2-9ab424255fec · outbound

This paper cites Computational Bottlenecks of Training Small-scale Large Language Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Computational Bottlenecks of Training Small-scale Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T05:36:22.608519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fdf5abf0-e0bd-4f9a-bdae-f098965e3f2c · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:15.887455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b742f291-5502-489f-b166-d41b08f40875 · outbound

This paper cites Qwen2.5-VL Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Qwen2.5-VL Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.008492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a759d4f8-f3aa-4161-8f46-b64515a7f480 · outbound

This paper cites Language Models are Few-Shot Learners.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Language Models are Few-Shot Learners

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.131300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5c417c-18a9-4dc0-9b18-847fb8334728 · outbound

This paper cites Matryoshka Multimodal Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Matryoshka Multimodal Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.252253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee21ce58-989d-4df0-9fc8-e76010ad85e2 · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.203133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf91c920-1571-41c4-88ac-1e15fe993083 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.550704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5094cf2c-ae6e-4a02-b93b-d71c7eb784b2 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.705692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2a78f9-20fd-4b6f-a7c4-36f3ba711a7f · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.823297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3ad882-5ad8-4422-9638-ed4c17654ccc · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:16.916546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beb49cf1-6177-438f-96b7-487fb8f11626 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:17.046484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b12cfc-f810-4ba5-b98f-1a3ff685a3d2 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:17.214634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff91f547-a92f-4e11-9933-3f2843efc94a · outbound

This paper cites PaddleOCR 3.0 Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning PaddleOCR 3.0 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:17.378776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec6b9c8-65b2-49c3-a151-68e7aaf1cc5b · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.149836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f842255c-0dea-46c9-b7ec-e60f46cf450c · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.121631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 99691d76-b85b-4bb9-8efa-7e0ccdc350e8 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:17.899494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931622a0-1b76-40a3-87c8-948eb6e1f4f6 · outbound

This paper cites Data Filtering Networks.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Data Filtering Networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:17.999665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04379f03-058a-4e4f-a9fe-3456385065b4 · outbound

This paper cites Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.071945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02266ad-6a60-4fe1-b239-5f8f1b6c1394 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.156872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168dbd3f-8959-4949-b2c4-8fe6331c5555 · outbound

This paper cites H.; Kamath, A.; Peng, N.; and Chang, K.-W.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning H.; Kamath, A.; Peng, N.; and Chang, K.-W

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:36:23.096804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e56ac321-f401-4885-848f-3fc84bc9692f · outbound

This paper cites Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.309017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe8d2891-1f27-40ee-8a9b-e9f96cbd28d8 · outbound

This paper cites Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.365077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d827b38b-0df4-4468-88e2-93219cf436a5 · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.069223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8e3065cc-a1d9-4c35-b585-c887a0bebd03 · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:23.021894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1f110178-b429-413f-a5fc-6688fa611a17 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning LLaVA-OneVision: Easy Visual Task Transfer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.580953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9c12d6-0d9a-4c28-8714-fb48617210fe · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.666785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d74209a-9cf5-4e68-97fb-7456a785e78c · outbound

This paper cites Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.779333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5abc18a0-57c1-41e4-9b75-a1c7165fae67 · outbound

This paper cites VILA: On Pre-training for Visual Language Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning VILA: On Pre-training for Visual Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.864386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af964230-1ca9-4adf-8b52-3362aa47d2c6 · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:18.949544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ca1f5d-f3fc-429d-a9ff-8e258dfbf45e · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:22.955843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6420b49e-5ddd-4161-a852-8fe376e436b7 · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:22.926566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cdf3d3c9-7768-4d90-a61e-bf7e1904a373 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.341740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16851500-9e0d-433d-a0a2-3a6a0604864e · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.420247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcae26e5-9d74-4f1b-b725-9d1175c24896 · outbound

This paper cites NVILA: Efficient Frontier Visual Language Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning NVILA: Efficient Frontier Visual Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.512240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f482c604-dbed-4c4b-a88a-e2bfae8f60fa · outbound

This paper cites Decoupled Weight Decay Regularization.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Decoupled Weight Decay Regularization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.605928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76420909-a476-4ec6-8430-31d05aa5cc23 · outbound

This paper cites BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.716602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf96d5d1-f44a-4e86-b065-e6a114834a41 · outbound

This paper cites Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:19.867128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a8c0152-c4cd-4521-b86a-ea08825139dc · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning SmolVLM: Redefining small and efficient multimodal models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.025302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340c3a01-ac8a-4fda-9dd5-eb288decbba2 · outbound

This paper cites MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.191131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e9096e5-a688-4227-b0e2-f1970f4eeb9d · outbound

This paper cites H.; Cao, Q.; Horton, M.; Jin, Y.; Sun, C.; Mirzadeh, S.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning H.; Cao, Q.; Horton, M.; Jin, Y.; Sun, C.; Mirzadeh, S

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:36:22.877808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 03bac653-3936-4554-bc9b-68a7324d64ef · outbound

This paper cites GPT-4 Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning GPT-4 Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.402653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e791c27-2820-460d-9d6f-b51d36decc48 · outbound

This paper cites Mobile Edge Intelligence for Large Language Models: A Contemporary Survey.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Mobile Edge Intelligence for Large Language Models: A Contemporary Survey

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.568916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4932a0-a3c4-4001-8fc4-5405e72c1adf · outbound

This paper cites W.; Hallacy, C.; Ramesh, A.; Goh, G.; Agarwal, S.; Sastry, G.; Askell, A.; Mishkin, P.; Clark, J.; et al.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning W.; Hallacy, C.; Ramesh, A.; Goh, G.; Agarwal, S.; Sastry, G.; Askell, A.; Mishkin, P.; Clark, J.; et al

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.695127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f396a20-9baf-49e2-9c7e-c2c8924d86c4 · outbound

This paper cites J.; and Yan, Y.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning J.; and Yan, Y

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.806605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcf31caa-61fe-4cf8-8152-0b803eaec2a8 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:20.951429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 204367c9-8c6e-4356-8b10-1497e7e306f2 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.049168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09744846-b49f-4163-ac75-237c81675511 · outbound

This paper cites C.; Yang, J.; Yang, S.; Iyer, A.; Pan, X.; Wang, A.; Fergus, R.; LeCun, Y.; and Xie, S.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning C.; Yang, J.; Yang, S.; Iyer, A.; Pan, X.; Wang, A.; Fergus, R.; LeCun, Y.; and Xie, S

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:36:22.817175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 035bffb9-8d16-4026-bd1b-4c5e03287061 · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.086476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af17a881-ca72-412c-8b27-d32eca853e68 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning LLaMA: Open and Efficient Foundation Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.095817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7affba21-a93b-40e3-a295-dde3a9805345 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.108741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbc1fc66-c4da-4a1a-95e0-cf6b897993fc · outbound

This paper cites H.; Wu, Y.; Le, Q.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning H.; Wu, Y.; Le, Q

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:36:22.789437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1bb5954-51c3-4ae1-a02b-6b51003b0a03 · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.122527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9701cd37-bc72-4fbe-aab4-75211c41a85a · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:22.765889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9fdfb4da-b154-47ef-9913-30c37e565476 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.132522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bec38ff-b4af-4ab2-98ed-3816e185f836 · outbound

This paper cites T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.140462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726c944d-d1f8-44ed-8119-4f8b9ca0bc80 · outbound

This paper cites Emergent Abilities of Large Language Models.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Emergent Abilities of Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.148753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb96f30-34c4-438f-addc-dc9902738ff9 · outbound

This paper cites PowerInfer-2: Fast Large Language Model Inference on a Smartphone.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.155515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbdfc907-9b57-400a-91e1-9337da8c6fee · outbound

This paper cites Qwen3 Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Qwen3 Technical Report

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.163843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e13913e-690f-415a-808b-5dd2ad160b16 · outbound

This paper cites Qwen2.5 Technical Report.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Qwen2.5 Technical Report

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.183605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1d00b8-d9ea-4111-95b0-e46810108f96 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.199932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47ecbe81-0a8c-43db-871f-ab1f316f792c · outbound

This paper cites an unresolved cited work.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-06T05:36:22.740875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa0571e1-fee6-4f6e-abeb-7fea0f01e71d · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.221692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3880fc57-0d21-4329-ad7d-e5250514dd13 · outbound

This paper cites LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.228925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c98efeb-8b81-40eb-80e0-7bc001648977 · outbound

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

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.235533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers