Nikolai Mozgovoi

vonexel's activity

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

upvoted 20 papers 6 days ago

FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation

Paper • 2609.11486 • Published Sep 10 • 14

Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

Paper • 2609.11317 • Published Sep 10 • 30

Learning Sparse Decision Trees via Transformer Variational Auto-Encoders

Paper • 2609.01430 • Published Sep 1 • 3

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published Sep 17 • 20

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

Paper • 2609.22255 • Published Sep 6 • 16

HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis

Paper • 2609.26793 • Published Sep 22 • 6

From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health

Paper • 2609.25186 • Published Sep 21 • 22

Rufus-Air: An Open LLM Post-Training Recipe

Paper • 2609.29421 • Published Sep 24 • 36

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

Paper • 2609.29845 • Published Sep 24 • 89

Training Object Permanence in World Models

Paper • 2609.28654 • Published Sep 23 • 97

Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem

Paper • 2609.30216 • Published Sep 24 • 13

D-JEPA: A Decision-Aligned Latent World Model

Paper • 2609.24749 • Published Sep 21 • 7

Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

Paper • 2609.24385 • Published Sep 21 • 17

WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing

Paper • 2608.18486 • Published Sep 27 • 6

Improving Test-Time Scaling with Adaptive Looped Transformers

Paper • 2609.35748 • Published Sep 28 • 63

Improved Distributional Diffusion Models

Paper • 2609.37147 • Published Sep 29 • 6

Jev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration

Paper • 2609.35342 • Published Sep 28 • 9

VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents

Paper • 2609.38119 • Published Sep 29 • 11

What Makes Recurrence Effective in Looped Language Models?

Paper • 2609.36636 • Published Sep 29 • 9

Adversarial Training for Pixel Diffusion

Paper • 2609.38170 • Published Sep 29 • 12