DmitryRyumin (Dmitry Ryumin)

reacted to prithivMLmods's post with 👍🚀❤️🤗 19 days ago

Post

3729

Made a small write up and experimental finetuning guide for MetaCLIP2 for Image Classification on Downstream Tasks. The blog titled Fine Tuning MetaCLIP 2 for Image Classification on Downstream Tasks demonstrates the step by step finetuning using CIFAR10 and is also flexible for adapting to other datasets. For more details, check out the linked blog below. 🤗↗️

⮞ Blog Article: https://huggingface.co/blog/prithivMLmods/metaclip2-downstream-finetune
⮞ Demo Space[Zero-Shot Classification]: prithivMLmods/metaclip-2-demo

Some other models
╰› MetaCLIP-2-Cifar10: prithivMLmods/MetaCLIP-2-Cifar10
╰› MetaCLIP-2-Age-Range-Estimator: prithivMLmods/MetaCLIP-2-Age-Range-Estimator
╰› MetaCLIP-2-Gender-Identifier: prithivMLmods/MetaCLIP-2-Gender-Identifier
╰› MetaCLIP-2-Open-Scene: prithivMLmods/MetaCLIP-2-Open-Scene

⮞ Collection: https://huggingface.co/collections/prithivMLmods/metaclip2-image-classification-experiments

To know more about it, visit the app page or the respective model page!

reacted to their post with 🔥 28 days ago

Post

1215

🚀👁️🌟 New Research Alert - ICCV 2025 (Poster)! 🌟👁️🚀
📄 Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation 🔝

📝 Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.

👥 Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)

📁 Repository: https://github.com/Jo-wang/TCA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight

posted an update 28 days ago

Post

1215

🚀👁️🌟 New Research Alert - ICCV 2025 (Poster)! 🌟👁️🚀
📄 Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation 🔝

📝 Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.

👥 Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)

📁 Repository: https://github.com/Jo-wang/TCA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight

reacted to their post with 👍 about 1 month ago

Post

2364

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching 🔝

📝 Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.

👥 Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)

📁 Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight

posted an update about 1 month ago

Post

2364

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching 🔝

📝 Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.

👥 Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)

📁 Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight

reacted to their post with 🤝🔥 about 1 month ago

Post

2828

🚀👌🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤌🚀
📄 Title: Understanding Co-speech Gestures in-the-wild 🔝

📝 Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.

👥 Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)

🌐 Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
📁 Repository: https://github.com/Sindhu-Hegde/jegal
📺 Video: https://www.youtube.com/watch?v=TYFOLKfM-rM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight

posted an update about 1 month ago

Post

2828

🚀👌🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤌🚀
📄 Title: Understanding Co-speech Gestures in-the-wild 🔝

📝 Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.

👥 Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)

🌐 Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
📁 Repository: https://github.com/Sindhu-Hegde/jegal
📺 Video: https://www.youtube.com/watch?v=TYFOLKfM-rM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight

reacted to their post with 🔥 about 1 month ago

Post

3944

🚀💡🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🪄🚀
📄 Title: LoftUp: Learning a Coordinate-based Feature Upsampler for Vision Foundation Models 🔝

📝 Description: LoftUp is a coordinate-based transformer that upscales the low-resolution features of VFMs (e.g. DINOv2 and CLIP) using cross-attention and self-distilled pseudo-ground truth (pseudo-GT) from SAM.

👥 Authors: Haiwen Huang, Anpei Chen, Volodymyr Havrylov, Andreas Geiger, and Dan Zhang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models (2504.14032)

🌐 Github Page: https://andrehuang.github.io/loftup-site
📁 Repository: https://github.com/andrehuang/loftup

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Foundation Models and Representation Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/foundation-models-and-representation-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #LoftUp #VisionFoundationModels #FeatureUpsampling #Cross-AttentionTransformer #CoordinateBasedLearning #SelfDistillation #PseudoGroundTruth #RepresentationLearning #AI #ICCV2025 #ResearchHighlight

posted an update about 1 month ago

Post

3944

🚀💡🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🪄🚀
📄 Title: LoftUp: Learning a Coordinate-based Feature Upsampler for Vision Foundation Models 🔝

📝 Description: LoftUp is a coordinate-based transformer that upscales the low-resolution features of VFMs (e.g. DINOv2 and CLIP) using cross-attention and self-distilled pseudo-ground truth (pseudo-GT) from SAM.

👥 Authors: Haiwen Huang, Anpei Chen, Volodymyr Havrylov, Andreas Geiger, and Dan Zhang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models (2504.14032)

🌐 Github Page: https://andrehuang.github.io/loftup-site
📁 Repository: https://github.com/andrehuang/loftup

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Foundation Models and Representation Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/foundation-models-and-representation-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #LoftUp #VisionFoundationModels #FeatureUpsampling #Cross-AttentionTransformer #CoordinateBasedLearning #SelfDistillation #PseudoGroundTruth #RepresentationLearning #AI #ICCV2025 #ResearchHighlight

reacted to their post with 🔥 about 1 month ago

Post

1943

🚀🏷️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🧩🚀
📄 Title: Heavy Labels Out! Dataset Distillation with Label Space Lightening 🔝

📝 Description: The HeLlO framework is a new corpus distillation method that removes the need for large soft labels. It uses a lightweight, online image-to-label projector based on CLIP. This projector has been adapted using LoRA-style, parameter-efficient tuning. It has also been initialized with text embeddings.

👥 Authors: @roseannelexie , @Huage001 , Zigeng Chen, Jingwen Ye, and Xinchao Wang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Heavy Labels Out! Dataset Distillation with Label Space Lightening (2408.08201)

📺 Video: https://www.youtube.com/watch?v=kAyK_3wskgA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #DatasetDistillation #LabelCompression #CLIP #LoRA #EfficientAI #FoundationModels #AI #ICCV2025 #ResearchHighlight

2 replies

·

posted an update about 1 month ago

Post

1943

🚀🏷️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🧩🚀
📄 Title: Heavy Labels Out! Dataset Distillation with Label Space Lightening 🔝

📝 Description: The HeLlO framework is a new corpus distillation method that removes the need for large soft labels. It uses a lightweight, online image-to-label projector based on CLIP. This projector has been adapted using LoRA-style, parameter-efficient tuning. It has also been initialized with text embeddings.

👥 Authors: @roseannelexie , @Huage001 , Zigeng Chen, Jingwen Ye, and Xinchao Wang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Heavy Labels Out! Dataset Distillation with Label Space Lightening (2408.08201)

📺 Video: https://www.youtube.com/watch?v=kAyK_3wskgA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #DatasetDistillation #LabelCompression #CLIP #LoRA #EfficientAI #FoundationModels #AI #ICCV2025 #ResearchHighlight

2 replies

·

reacted to their post with 🔥 about 1 month ago

Post

4802

🚀🤖🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤖🚀
📄 Title: Variance-based Pruning for Accelerating and Compressing Trained Networks 🔝

📝 Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.

👥 Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight

posted an update about 1 month ago

Post

4802

🚀🤖🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤖🚀
📄 Title: Variance-based Pruning for Accelerating and Compressing Trained Networks 🔝

📝 Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.

👥 Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight

reacted to their post with 🔥 about 1 month ago

Post

3006

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Token Activation Map to Visually Explain Multimodal LLMs 🔝

📝 Description: The Token Activation Map (TAM) is an advanced explainability method for multimodal LLMs. Using causal inference and a Rank Gaussian Filter, TAM reveals token-level interactions and eliminates redundant activations. The result is clearer, high-quality visualizations that enhance understanding of object localization, reasoning and multimodal alignment across models.

👥 Authors: Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, and Xiaomeng Li

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Token Activation Map to Visually Explain Multimodal LLMs (2506.23270)

📁 Repository: https://github.com/xmed-lab/TAM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Multi-Modal Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/multi-modal-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TokenActivationMap #TAM #CausalInference #VisualReasoning #Multimodal #Explainability #VisionLanguage #LLM #XAI #AI #ICCV2025 #ResearchHighlight

2 replies

·

posted an update about 1 month ago

Post

3006

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Token Activation Map to Visually Explain Multimodal LLMs 🔝

📝 Description: The Token Activation Map (TAM) is an advanced explainability method for multimodal LLMs. Using causal inference and a Rank Gaussian Filter, TAM reveals token-level interactions and eliminates redundant activations. The result is clearer, high-quality visualizations that enhance understanding of object localization, reasoning and multimodal alignment across models.

👥 Authors: Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, and Xiaomeng Li

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Token Activation Map to Visually Explain Multimodal LLMs (2506.23270)

📁 Repository: https://github.com/xmed-lab/TAM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Multi-Modal Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/multi-modal-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TokenActivationMap #TAM #CausalInference #VisualReasoning #Multimodal #Explainability #VisionLanguage #LLM #XAI #AI #ICCV2025 #ResearchHighlight

2 replies

·

reacted to merve's post with 🔥 6 months ago

Post

2535

#CVPR2025 Paper Picks #1
VisionZip is a compression technique that reduces number of visual tokens to improve performance AND prefill time for vision language models
demo: Senqiao/VisionZip
paper: VisionZip: Longer is Better but Not Necessary in Vision Language Models (2412.04467)
most of the image tokens are redundant for the LLM, so the authors ask "are all visual tokens necessary?"

the method is simple:
find which tokens have the highest attention score, merge rest of the tokens based on similarity, then merge both

their method is both training-free and for fine-tuning
the authors report 5 point improvement on average of vision language tasks + 8x improvement in prefilling time for Llava-Next 7B and 13B 🤯

removing redundant tokens improve image token quality too 🥹

Dmitry Ryumin

AI & ML interests

Recent Activity

Organizations

Dmitry Ryumin

AI & ML interests

Recent Activity

Organizations

DmitryRyumin's activity