Artem

kabachuha's activity

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

upvoted an article about 16 hours ago

view article

Article

FLUX 3 Action: a world action model you can fine-tune

• 

black-forest-labs

•

about 17 hours ago

• 5

upvoted a collection about 19 hours ago

Kandinsky-6.0-S2V

Collection

Kandinsky-6.0-S2V • 9 items • Updated about 7 hours ago • 2

upvoted a collection 14 days ago

Kandinsky-6.0-VSR

Collection

6 items • Updated 3 days ago • 2

upvoted a collection about 1 month ago

LTX-2.5

Collection

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs • 5 items • Updated 15 days ago • 65

upvoted a paper about 2 months ago

KVAE: Family of Tokenizers for Multimodal Generative Models

Paper • 2608.05798 • Published Aug 6 • 29

upvoted 2 collections about 2 months ago

Kandinsky WM 1.0

Collection

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

Laguna S 2.1

Collection

Our most capable model to date, designed for long-horizon work. • 13 items • Updated Aug 3 • 51

upvoted 2 papers 3 months ago

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Paper • 2607.02515 • Published Jul 2 • 21

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 82

upvoted 3 papers 4 months ago

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

Paper • 2606.10029 • Published Jun 8 • 12

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Paper • 2606.06735 • Published Jun 4 • 27

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

Paper • 2606.07473 • Published Jun 5 • 15

upvoted an article 4 months ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

Jun 1

• 90

upvoted a collection 5 months ago

KVAE 2.0

Collection

KVAE 2.0 is a family of image and video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16 • 3 items • Updated Aug 6 • 5

upvoted a paper 6 months ago

Interpreting CLIP with Hierarchical Sparse Autoencoders

Paper • 2502.20578 • Published Feb 27, 2025 • 1

upvoted a collection 6 months ago

My LTX-2 Loras

Collection

9 items • Updated Apr 3 • 7

upvoted 2 papers 7 months ago

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models

Paper • 2511.08379 • Published Nov 11, 2025 • 5

Effective Reasoning Chains Reduce Intrinsic Dimensionality

Paper • 2602.09276 • Published Feb 9 • 12

upvoted 2 papers 8 months ago

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published Feb 9 • 71

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published Feb 4 • 63