Vladimir Korviakov

korviakov's activity

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

upvoted a paper about 16 hours ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 2 days ago • 58

upvoted a collection about 1 month ago

Kandinsky WM 1.0

Collection

Image-to-Video models for Physical AI: autonomous driving, robotics, general physics. • 3 items • Updated Aug 4 • 6

upvoted 2 papers about 2 months ago

KVAE: Family of Tokenizers for Multimodal Generative Models

Paper • 2608.05798 • Published Aug 6 • 29

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Paper • 2608.08311 • Published Aug 8 • 95

upvoted a paper 3 months ago

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Paper • 2606.19297 • Published Jun 17 • 78

upvoted a paper 4 months ago

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Paper • 2606.06735 • Published Jun 4 • 27

upvoted a collection 6 months ago

Calibri models

Collection

2 items • Updated Mar 27 • 4

upvoted a paper 7 months ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 57

upvoted 2 papers 8 months ago

Rethinking Global Text Conditioning in Diffusion Transformers

Paper • 2602.09268 • Published Feb 9 • 9

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published Jan 31 • 322

upvoted 4 papers 10 months ago

RELIC: Interactive Video World Model with Long-Horizon Memory

Paper • 2512.04040 • Published Dec 3, 2025 • 24

Video Generation Models Are Good Latent Reward Models

Paper • 2511.21541 • Published Nov 26, 2025 • 51

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17, 2025 • 122

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published Nov 19, 2025 • 91

upvoted a collection 10 months ago

Kandinsky 5.0 Video Pro

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 5 items • Updated Jul 29 • 20

upvoted a paper 10 months ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 236

upvoted a collection 12 months ago

Kandinsky 5.0

Collection

9 items • Updated Nov 7, 2025 • 33

upvoted a paper 12 months ago

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Paper • 2509.20427 • Published Sep 24, 2025 • 89

upvoted 2 papers about 1 year ago

nablaNABLA: Neighborhood Adaptive Block-Level Attention

Paper • 2507.13546 • Published Jul 17, 2025 • 126

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published Jul 8, 2025 • 121