53 114 183

Dmitry Ryumin

DmitryRyumin

https://dmitryryumin.github.io

DmitryRyumin

AI & ML interests

Machine Learning and Applications, Multi-Modal Understanding

Recent Activity

upvoted an article 20 days ago

Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks

reacted to prithivMLmods's post with 👍 20 days ago

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]: https://huggingface.co/spaces/prithivMLmods/metaclip-2-demo Some other models ╰› MetaCLIP-2-Cifar10: https://huggingface.co/prithivMLmods/MetaCLIP-2-Cifar10 ╰› MetaCLIP-2-Age-Range-Estimator: https://huggingface.co/prithivMLmods/MetaCLIP-2-Age-Range-Estimator ╰› MetaCLIP-2-Gender-Identifier: https://huggingface.co/prithivMLmods/MetaCLIP-2-Gender-Identifier ╰› MetaCLIP-2-Open-Scene: https://huggingface.co/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 prithivMLmods's post with 🚀 20 days ago

View all activity

Organizations

upvoted an article 20 days ago

Article

Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks

21 days ago

•

upvoted a paper 29 days ago

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

Paper • 2511.02818 • Published Nov 4 • 15

upvoted 9 papers about 1 month ago

SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing

Paper • 2509.11265 • Published Sep 14 • 1

Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning

Paper • 2509.17971 • Published Sep 22 • 1

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published Oct 28 • 96

Token Activation Map to Visually Explain Multimodal LLMs

Paper • 2506.23270 • Published Jun 29 • 5

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

Paper • 2504.14032 • Published Apr 18 • 7

Knocking-Heads Attention

Paper • 2510.23052 • Published Oct 27 • 29

E^2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

Paper • 2510.22733 • Published Oct 26 • 31

Heavy Labels Out! Dataset Distillation with Label Space Lightening

Paper • 2408.08201 • Published Aug 15, 2024 • 21

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Paper • 2510.19779 • Published Oct 22 • 59

upvoted 3 papers about 2 months ago

Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding

Paper • 2510.06308 • Published Oct 7 • 53

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Paper • 2510.06590 • Published Oct 8 • 72

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Paper • 2510.03215 • Published Oct 3 • 97

upvoted 3 collections 2 months ago

upvoted 2 papers 2 months ago

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24 • 98

FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

Paper • 2509.17177 • Published Sep 21 • 13

upvoted a collection 2 months ago

Qwen3-Omni

Collection

6 items • Updated Oct 9 • 166

Dmitry Ryumin

AI & ML interests

Recent Activity

Organizations

DmitryRyumin's activity

Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks