martin's picture

martin PRO

martintomov

·

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

arnaudstiegler/sd-model-gameNgen-60ksteps

reacted to merve's post with 🚀 8 days ago

Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models 🧶 ✨ the models come in 1.5B https://huggingface.co./Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co./Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co./Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2 ✨ the authors also release a benchmark dataset https://huggingface.co./spaces/Apollo-LMMs/ApolloBench The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work ⏯️ Try the demo for best setup here https://huggingface.co./spaces/Apollo-LMMs/Apollo-3B they evaluate sampling strategies, scaling laws for models and datasets, video representation and more! > The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled 📈 scaling dataset has diminishing returns for smaller models > They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal > They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2 they find https://huggingface.co./google/siglip-so400m-patch14-384 to be most powerful 🔥 > they also compare freezing different parts of models, training all stages with some frozen parts give the best yield They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models 🔥

liked a model 8 days ago

FastVideo/FastMochi

View all activity

Organizations

martintomov's activity

upvoted a collection 16 days ago

[MASK] is All You Need

Code, dataset, and pretrained model • 5 items • Updated 27 days ago • 8

upvoted a paper 20 days ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published 21 days ago • 118

upvoted a collection 20 days ago

PaliGemma 2 Release

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 23 items • Updated 12 days ago • 119

upvoted a paper about 1 month ago

OminiControl: Minimal and Universal Control for Diffusion Transformer

Paper • 2411.15098 • Published Nov 22 • 53

upvoted a collection about 1 month ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 28 days ago • 444

upvoted 3 papers about 1 month ago

MagicQuill: An Intelligent Interactive Image Editing System

Paper • 2411.09703 • Published Nov 14 • 57

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

Paper • 2411.07232 • Published Nov 11 • 62

Qwen2.5-Coder Technical Report

Paper • 2409.12186 • Published Sep 18 • 138

upvoted 4 papers about 2 months ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

Paper • 2411.04928 • Published Nov 7 • 48

Adding Conditional Control to Text-to-Image Diffusion Models

Paper • 2302.05543 • Published Feb 10, 2023 • 43

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17 • 108

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

Paper • 2410.19355 • Published Oct 25 • 23

upvoted 3 papers 3 months ago

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Paper • 2409.18124 • Published Sep 26 • 32

Imagine yourself: Tuning-Free Personalized Image Generation

Paper • 2409.13346 • Published Sep 20 • 68

A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis

Paper • 2409.08947 • Published Sep 13 • 11

upvoted a collection 4 months ago

Hermes 3

The Hermes 3 Series of Models • 10 items • Updated 14 days ago • 101

upvoted 2 papers 4 months ago

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Paper • 2408.08152 • Published Aug 15 • 52

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Paper • 2408.06070 • Published Aug 12 • 53

upvoted a collection 5 months ago

MaPO

This collection includes the models and datasets as a part of the MaPO release. • 9 items • Updated Jun 12 • 5

upvoted an article 5 months ago

Article

XetHub is joining Hugging Face!

Aug 8

• 81