Oleg Lavrovsky PRO

loleg

·

AI & ML interests

Supporting Apertus team / Organizing hackathons / Engaged for open data

Recent Activity

liked a Space about 5 hours ago

jaredpalmer/kev

liked a model about 7 hours ago

NemoStation/Marlin-2B

liked a model about 8 hours ago

mistralai/Pixtral-12B-2409

View all activity

Organizations

upvoted a collection 2 days ago

Stentor1

The Stentor1 series is StentorLabs’ first family of transparent 12M- and 30M-parameter Llama-style models trained from scratch on free-tier hardware. • 4 items • Updated Feb 28 • 3

upvoted an article 3 days ago

Article

Your Agent Aced the Task. Will It Do It Again?

ibm-research

•

11 days ago

• 114

upvoted a paper 7 days ago

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published 12 days ago • 66

upvoted 5 papers 13 days ago

Last Translation Benchmark

Paper • 2609.04173 • Published 24 days ago • 43

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 24 days ago • 101

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published 24 days ago • 186

SingProbe Technical Report

Paper • 2608.30703 • Published 27 days ago • 11

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5, 2025 • 66

upvoted a collection 17 days ago

OlmoEarth

OlmoEarth pre-trained and fine-tuned foundation models for remote sensing • 18 items • Updated Jun 29 • 37

upvoted a paper 19 days ago

SLANT: Spurious Logo ANalysis Toolkit

Paper • 2406.01449 • Published Jun 3, 2024 • 1

upvoted a collection 20 days ago

Cosmos3

Omnimodal World Models for Physical AI • 6 items • Updated 30 days ago • 203

upvoted 2 articles 20 days ago

Article

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

nvidia

•

Aug 10

• 38

Article

Build Small Hackathon With Cohere Models

CohereLabs

•

Jun 4

• 9

upvoted a collection 22 days ago

K2 Horizon

K2 Horizon models, datasets, and supporting resources • 22 items • Updated 16 days ago • 135

upvoted a paper 23 days ago

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Paper • 2607.25948 • Published Jul 28 • 16

upvoted a collection 23 days ago

Awesome feedback datasets

A curated list of datasets with human or AI feedback. Useful for training reward models or applying techniques like DPO. • 19 items • Updated Aug 3 • 71

upvoted a paper 23 days ago

Unified and Efficient Point-Line Local Features

Paper • 2608.19894 • Published Aug 20 • 1

upvoted an article 24 days ago

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

EuroBERT

•

Mar 10, 2025

• 150

upvoted a paper about 1 month ago

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published Feb 3 • 42

upvoted an article about 1 month ago

Article

Making Knowledge Distillation Cheap Enough to Run at Scale

MultiverseComputingCAI

•

Aug 10

• 42