Research graph
References from Revisiting InternVL: A Systematic Technical Framework for Building Powerful Open-Source Vision-Language Models. Local targets link to admitted publications; unresolved targets remain external evidence.
GPT-4V(ision) system card
2023 · External reference
GPT-4O system card
2024 · External reference
Introducing GPT-5
2025 · External reference
Gemini: A family of highly capable multimodal models
2023 · External reference
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
2024 · External reference
Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities
2025 · External reference
Gemini 3 pro - model card
2025 · External reference
Qwen-Vl: A frontier large vision-language model with versatile abilities
2023 · External reference
Qwen2-Vl: Enhancing vision-language model’s perception of the world at any resolution
2024 · External reference
Qwen2.5-Vl technical report
2025 · External reference
Qwen3-Vl technical report
2025 · External reference
10.1109/cvpr52733.2024.02283
10.1109/cvpr52733.2024.02283 · External reference
10.1007/s11432-024-4231-5
10.1007/s11432-024-4231-5 · External reference
Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling
2024 · External reference
InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models
2025 · External reference
Eagle: Exploring the design space for multimodal LLMs with mixture of encoders
External reference
Eagle 2: Building post-training data strategies from scratch for frontier vision-language models
2025 · External reference
10.52202/085713-3047
10.52202/085713-3047 · External reference
10.52202/079017-3860
10.52202/079017-3860 · External reference
CogVLM2: Visual language models for image and video understanding
2024 · External reference
MiniCPM-V: A GPT-4V level MLLM on your phone
2024 · External reference
MiniCPM-V4.5: Cooking efficient MLLMs via architecture, data, and training recipe
2025 · External reference
Deepseek-Vl: Towards real-world vision-language understanding
2024 · External reference
Deepseek-Vl2: Mixture-of-experts vision-language models for advanced multimodal understanding
2024 · External reference
10.52202/075280-1516
10.52202/075280-1516 · External reference
10.1109/cvpr52733.2024.02484
10.1109/cvpr52733.2024.02484 · External reference
LLaVA-onevision: Easy visual task transfer
2025 · External reference
LLaVA-onevision-1.5: Fully open framework for democratized multimodal training
2025 · External reference
InternLM2 technical report
2024 · External reference
Qwen2 technical report
2024 · External reference
Qwen3 technical report
2025 · External reference
Learning transferable visual models from natural language supervision
External reference
10.1109/iccv51070.2023.01100
10.1109/iccv51070.2023.01100 · External reference
10.1109/cvpr52733.2024.02520
10.1109/cvpr52733.2024.02520 · External reference
10.1109/cvpr52734.2025.00390
10.1109/cvpr52734.2025.00390 · External reference
10.1109/cvpr52688.2022.01553
10.1109/cvpr52688.2022.01553 · External reference
BEiT: Bert pre-training of image transformers
External reference
BEiT V2: Masked image modeling with vector-quantized visual tokenizers
2022 · External reference
10.1109/cvpr52729.2023.01838
10.1109/cvpr52729.2023.01838 · External reference
10.1109/cvpr52729.2023.01855
10.1109/cvpr52729.2023.01855 · External reference
10.1016/j.imavis.2024.105171
10.1016/j.imavis.2024.105171 · External reference
DINOv2: Learning robust visual features without supervision
2024 · External reference
EVA-clip: Improved training techniques for clip at scale
2023 · External reference
MM1: Methods, analysis and insights from multimodal LLM pre-training
External reference
MM1.5: Methods, analysis & insights from multimodal LLM fine-tuning
External reference
Molmo and PixMo: Open weights and open data for state-of-the-art multimodal models
2024 · External reference
SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features
2025 · External reference
10.1109/cvpr52734.2025.00901
10.1109/cvpr52734.2025.00901 · External reference
10.52202/075280-0106
10.52202/075280-0106 · External reference
10.52202/075280-3155
10.52202/075280-3155 · External reference
Introducing our multimodal models
2023 · External reference
The Llama 4 herd: Architecture, training, evaluation, and deployment notes
2026 · External reference
10.48550/arxiv.2010.11929
10.48550/arxiv.2010.11929 · External reference
Scaling vision transformers to 22 billion parameters
External reference
Root mean square layer normalization
External reference
10.52202/068431-1833
10.52202/068431-1833 · External reference
LLaMA: Open and efficient foundation language models
2023 · External reference
Laion COCO: 600M synthetic captions from laion2B-en
2022 · External reference
Coyo-700M: Image-text pair dataset
2022 · External reference
10.52202/068431-1916
10.52202/068431-1916 · External reference
10.1109/cvpr46437.2021.00356
10.1109/cvpr46437.2021.00356 · External reference
10.18653/v1/p18-1238
10.18653/v1/p18-1238 · External reference
Im2Text: Describing images using 1 million captioned photographs
External reference
10.1109/cvpr52729.2023.02240
10.1109/cvpr52729.2023.02240 · External reference
PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system
2022 · External reference
10.1007/s44267-024-00067-6
10.1007/s44267-024-00067-6 · External reference
10.1109/iccv51701.2025.01958
10.1109/iccv51701.2025.01958 · External reference
Phi-3 technical report: A highly capable language model locally on your phone
2024 · External reference
YI: Open foundation models by 01.AI
2024 · External reference
The Llama 3 herd of models
2024 · External reference
SmoLLM-corpus
External reference
10.18653/v1/2025.findings-acl.206
10.18653/v1/2025.findings-acl.206 · External reference
SCP-116K: A high-quality problem-solution dataset and a generalized pipeline for automated extraction in the higher education science domain
2025 · External reference
10.1109/cvpr52729.2023.00276
10.1109/cvpr52729.2023.00276 · External reference
10.1109/iccv51070.2023.00505
10.1109/iccv51070.2023.00505 · External reference
10.1109/cvpr.2009.5206848
10.1109/cvpr.2009.5206848 · External reference
Are we done with imagenet?
2020 · External reference
Do imageNet classifiers generalize to imagenet?
External reference
10.1109/cvpr46437.2021.01501
10.1109/cvpr46437.2021.01501 · External reference
10.1109/iccv48922.2021.00823
10.1109/iccv48922.2021.00823 · External reference
Learning robust global representations by penalizing local predictive power
External reference
10.1007/978-3-030-01228-1_26
10.1007/978-3-030-01228-1_26 · External reference
10.1109/cvpr.2017.544
10.1109/cvpr.2017.544 · External reference
10.1109/cvpr.2018.00132
10.1109/cvpr.2018.00132 · External reference
Enhancing the reasoning ability of multimodal large language models via mixed preference optimization
2024 · External reference
Deepseekmath: Pushing the limits of mathematical reasoning in open language models
2024 · External reference
MBBench: Is your multi-modal model an all-around player?
External reference
10.52202/079017-0850
10.52202/079017-0850 · External reference
10.1109/cvpr52733.2024.00913
10.1109/cvpr52733.2024.00913 · External reference
MathVista: Evaluating mathematical reasoning of foundation models in visual contexts
External reference
10.1109/cvpr52733.2024.01363
10.1109/cvpr52733.2024.01363 · External reference
10.1007/978-3-319-46493-0_15
10.1007/978-3-319-46493-0_15 · External reference
10.1007/s11432-024-4235-6
10.1007/s11432-024-4235-6 · External reference
MM-Vet: Evaluating large multimodal models for integrated capabilities
External reference
Infinity-MM: Scaling multimodal performance with large-scale and high-quality instruction data
2024 · External reference
Ovis: Structural embedding alignment for multimodal large language model
2024 · External reference
10.52202/079017-2771
10.52202/079017-2771 · External reference
The claude 3 model family: Opus, sonnet, haiku
2024 · External reference
NVLM: Open frontier-class multimodal LLMs
2024 · External reference
10.18653/v1/2022.findings-acl.177
10.18653/v1/2022.findings-acl.177 · External reference
10.1109/cvpr.2019.00851
10.1109/cvpr.2019.00851 · External reference
10.1109/wacv48630.2021.00225
10.1109/wacv48630.2021.00225 · External reference
10.1109/wacv51458.2022.00264
10.1109/wacv51458.2022.00264 · External reference
10.1109/cvpr52733.2024.01263
10.1109/cvpr52733.2024.01263 · External reference
10.52202/079017-3609
10.52202/079017-3609 · External reference
VCR: Visual caption restoration
2024 · External reference
10.1007/978-3-031-73337-6_9
10.1007/978-3-031-73337-6_9 · External reference
MANTIS: Interleaved multi-image instruction tuning
2024 · External reference
MMIU: Multimodal multi-image understanding for evaluating large vision-language models
External reference
MuirBench: A comprehensive benchmark for robust multi-image understanding
External reference
MMT-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask AGI
External reference
Benchmarking multi-image understanding in vision and language models: Perception, knowledge, reasoning, and multi-hop reasoning
2024 · External reference
Grok-1.5 vision preview
2024 · External reference
MME-realworld: Could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans?
External reference
10.52202/079017-1528
10.52202/079017-1528 · External reference
10.1109/jstsp.2025.3558652
10.1109/jstsp.2025.3558652 · External reference
10.3115/v1/d14-1086
10.3115/v1/d14-1086 · External reference
10.1109/cvpr.2016.9
10.1109/cvpr.2016.9 · External reference
10.1007/978-3-031-72970-6_3
10.1007/978-3-031-72970-6_3 · External reference
10.1109/cvpr52729.2023.01471
10.1109/cvpr52729.2023.01471 · External reference
One-peace: Exploring one general representation model toward unlimited modalities
2023 · External reference
Shikra: Unleashing multimodal LLM’s referential dialogue magic
2023 · External reference
Ferret-V2: An improved baseline for referring and grounding with large language models
2024 · External reference
TextHawk2: A large vision-language model excels in bilingual ocr and grounding with 16x fewer tokens
2024 · External reference
10.1007/s11432-024-4321-9
10.1007/s11432-024-4321-9 · External reference
Oryx MLLM: On-demand spatial-temporal understanding at arbitrary resolution
External reference
VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs
2024 · External reference
10.1109/cvpr52734.2025.02245
10.1109/cvpr52734.2025.02245 · External reference
10.1109/cvpr52733.2024.02095
10.1109/cvpr52733.2024.02095 · External reference
10.52202/079017-2827
10.52202/079017-2827 · External reference
10.1109/cvpr52734.2025.01278
10.1109/cvpr52734.2025.01278 · External reference
10.52202/079017-0907
10.52202/079017-0907 · External reference
10.52202/068431-1189
10.52202/068431-1189 · External reference
10.1109/cvpr.2018.00380
10.1109/cvpr.2018.00380 · External reference
10.1109/cvpr.2019.00686
10.1109/cvpr.2019.00686 · External reference
10.52202/068431-0182
10.52202/068431-0182 · External reference
10.18653/v1/2023.emnlp-main.20
10.18653/v1/2023.emnlp-main.20 · External reference
Tiny LVLM-ehub: Early multimodal experiments with bard
2023 · External reference
Seed-bench: Benchmarking multimodal LLMs with generative comprehension
2023 · External reference
10.52202/079017-3014
10.52202/079017-3014 · External reference
10.1007/978-3-031-73242-3_10
10.1007/978-3-031-73242-3_10 · External reference
DynaMath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models
External reference
10.18653/v1/2025.acl-long.983
10.18653/v1/2025.acl-long.983 · External reference
LogicVista: Multimodal LLM logical reasoning benchmark in visual contexts
2024 · External reference
Measuring massive multitask language understanding
External reference
10.18653/v1/2024.findings-acl.671
10.18653/v1/2024.findings-acl.671 · External reference
C-EVAL: A multi-level multi-discipline chinese evaluation suite for foundation models
10.52202/075280-2749 · External reference
Evaluating the performance of large language models on gaokao benchmark
2023 · External reference
10.18653/v1/p17-1147
10.18653/v1/p17-1147 · External reference
10.1162/tacl_a_00276
10.1162/tacl_a_00276 · External reference
10.1162/tacl_a_00305
10.1162/tacl_a_00305 · External reference
10.18653/v1/d17-1082
10.18653/v1/d17-1082 · External reference
10.1609/aaai.v34i05.6399
10.1609/aaai.v34i05.6399 · External reference
10.18653/v1/p19-1472
10.18653/v1/p19-1472 · External reference
10.18653/v1/2023.findings-acl.824
10.18653/v1/2023.findings-acl.824 · External reference
Training verifiers to solve math word problems
2021 · External reference
Measuring mathematical problem solving with the MATH dataset
2021 · External reference
10.18653/v1/2023.emnlp-main.489
10.18653/v1/2023.emnlp-main.489 · External reference
Evaluating large language models trained on code
2021 · External reference
Program synthesis with large language models
2021 · External reference
