Dmitry Ryumin's picture

Dmitry Ryumin

DmitryRyumin

·

https://dmitryryumin.github.io

DmitryRyumin

AI & ML interests

Machine Learning and Applications, Multi-Modal Understanding

Recent Activity

reacted to their post with 🔥 about 10 hours ago

🚀💡🌟 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: https://huggingface.co/papers/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 https://huggingface.co/spaces/DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin 🔍 Keywords: #LoftUp #VisionFoundationModels #FeatureUpsampling #Cross-AttentionTransformer #CoordinateBasedLearning #SelfDistillation #PseudoGroundTruth #RepresentationLearning #AI #ICCV2025 #ResearchHighlight

posted an update about 10 hours ago

🚀💡🌟 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: https://huggingface.co/papers/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 https://huggingface.co/spaces/DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin 🔍 Keywords: #LoftUp #VisionFoundationModels #FeatureUpsampling #Cross-AttentionTransformer #CoordinateBasedLearning #SelfDistillation #PseudoGroundTruth #RepresentationLearning #AI #ICCV2025 #ResearchHighlight

upvoted a paper about 10 hours ago

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

View all activity

Organizations

upvoted a paper about 10 hours ago

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

Paper • 2504.14032 • Published Apr 18 • 6

upvoted 2 papers about 15 hours ago

Knocking-Heads Attention

Paper • 2510.23052 • Published 2 days ago • 22

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

Paper • 2510.22733 • Published 3 days ago • 29

upvoted a paper 1 day ago

Heavy Labels Out! Dataset Distillation with Label Space Lightening

Paper • 2408.08201 • Published Aug 15, 2024 • 21

upvoted a paper 2 days ago

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Paper • 2510.19779 • Published 6 days ago • 58

upvoted 3 papers 19 days ago

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

Paper • 2510.06308 • Published 21 days ago • 52

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

Paper • 2510.06590 • Published 21 days ago • 70

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

Paper • 2510.03215 • Published 25 days ago • 93

upvoted a collection 24 days ago

Kandinsky 5.0 T2V Lite

8 items • Updated 29 days ago • 30

upvoted a collection 26 days ago

Granite 4.0

IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth. • 38 items • Updated about 17 hours ago • 19

upvoted a collection about 1 month ago

Gemma 3n

4 items • Updated Jul 10 • 234

upvoted 2 papers about 1 month ago

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24 • 96

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 2 collections about 1 month ago

Qwen3-Omni

6 items • Updated 20 days ago • 161

Qwen3-VL

25 items • Updated 8 days ago • 336

upvoted a collection about 2 months ago

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 26 items • Updated Sep 24 • 174

upvoted a paper about 2 months ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25 • 201

upvoted an article about 2 months ago

Article

Open Datasets and Tools: An overview for Hugging Face

By

•

Aug 27

• 4

upvoted a collection about 2 months ago

Hunyuan-MT

4 items • Updated 4 days ago • 36

upvoted a paper 3 months ago

Voxtral

Paper • 2507.13264 • Published Jul 17 • 29