Denis Dimitrov

dendimitrov's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 1 month ago

$\nabla$NABLA: Neighborhood Adaptive Block-Level Attention

Paper • 2507.13546 • Published Jul 17 • 120

upvoted a paper about 1 month ago

nablaNABLA: Neighborhood Adaptive Block-Level Attention

Paper • 2507.13546 • Published Jul 17 • 120

upvoted a paper 3 months ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5 • 130

liked a Space 5 months ago

Running

263

263

Qwen2.5 VL 72B Instruct

💻

Interact with Qwen2.5-VL-72B to chat and upload files

upvoted 2 papers 6 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24 • 121

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20 • 73

liked a Space 6 months ago

Runtime error

12

12

GHOST 2.0

🖼

Swap faces in images

authored 2 papers 6 months ago

MERA: A Comprehensive LLM Evaluation in Russian

Paper • 2401.04531 • Published Jan 9, 2024 • 2

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 68

upvoted a paper 6 months ago

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 68

upvoted 2 papers about 1 year ago

Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion

Paper • 2407.13759 • Published Jul 18, 2024 • 18

Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Paper • 2310.03502 • Published Oct 5, 2023 • 78

authored 6 papers about 1 year ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19, 2024 • 159

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9, 2024 • 78

Kandinsky 3.0 Technical Report

Paper • 2312.03511 • Published Dec 6, 2023 • 46

Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Paper • 2310.03502 • Published Oct 5, 2023 • 78

Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction

Paper • 2202.00441 • Published Feb 1, 2022 • 1

Digital Peter: Dataset, Competition and Handwriting Recognition Methods

Paper • 2103.09354 • Published Mar 16, 2021

upvoted a paper about 1 year ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19, 2024 • 159

authored a paper about 1 year ago

FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline

Paper • 2311.13073 • Published Nov 22, 2023 • 58