Oleg Lavrovsky PRO

loleg's activity

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

upvoted an article 2 days ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

3 days ago

•

515

upvoted a paper 3 days ago

Are complicated loss functions necessary for teaching LLMs to reason?

Paper • 2603.18756 • Published 17 days ago • 1

upvoted 2 papers 6 days ago

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published 10 days ago • 125

Voxtral TTS

Paper • 2603.25551 • Published 9 days ago • 56

upvoted a paper 10 days ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 21

upvoted a collection 10 days ago

Global PIQA

Collection

A physical commonsense reasoning benchmark for 100+ languages, written in collaboration with 300+ researchers from 65 countries. • 2 items • Updated Feb 2 • 2

upvoted a paper 11 days ago

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 41

upvoted a paper 19 days ago

Tracking Capabilities for Safer Agents

Paper • 2603.00991 • Published Mar 1 • 2

upvoted a changelog 23 days ago

view changelog

Hugging Face Changelog

Public Storage Add-ons

Feb 26

• 168

upvoted 3 articles 23 days ago

view article

Article

LeRobot v0.5.0: Scaling Every Dimension

• 
• 
• +8

27 days ago

•

38

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

26 days ago

•

103

view article

Article

How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II

• 

24 days ago

•

30

upvoted a paper about 1 month ago

Biased Tales: Cultural and Topic Bias in Generating Children's Stories

Paper • 2509.07908 • Published Sep 9, 2025 • 1

upvoted 2 papers about 2 months ago

Parallel Scaling Law for Language Models

Paper • 2505.10475 • Published May 15, 2025 • 83

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Paper • 2601.06021 • Published Jan 9 • 47

upvoted an article about 2 months ago

view article

Article

Hopper: The Optimizer That Learns Parallelism 2x Faster Than Adam

• 

Feb 6

•

4

upvoted 3 collections about 2 months ago

ACE

Collection

Ai2 Climate Emulator (ACE) is a family of fast ML models that simulate global atmospheric variability over time scales ranging from hours to centuries • 9 items • Updated 22 days ago • 13

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated Mar 2 • 88

Molmo2

Collection

Artifacts for the Molmo2 release • 5 items • Updated Mar 2 • 36

upvoted a paper about 2 months ago

EuroLLM-22B: Technical Report

Paper • 2602.05879 • Published Feb 5 • 3