Eugene Oskin

eoskin's activity

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

upvoted a collection 1 day ago

Qwen3-TTS

Collection

7 items • Updated Jan 22 • 330

upvoted an article 1 day ago

view article

Article

Sentence Transformers is joining Hugging Face!

• 

Oct 22, 2025

•

88

upvoted a paper 3 days ago

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

Paper • 2603.12228 • Published 10 days ago • 11

upvoted 2 papers 9 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19, 2025 • 217

AutoHarness: improving LLM agents by automatically synthesizing a code harness

Paper • 2603.03329 • Published Feb 10 • 1

upvoted an article 11 days ago

view article

Article

Introducing Storage Buckets on the Hugging Face Hub

• 
• 
• +10

13 days ago

•

183

upvoted a collection 20 days ago

Jan-code

Collection

2 items • Updated 20 days ago • 19

upvoted 2 papers 20 days ago

AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games

Paper • 2602.17594 • Published about 1 month ago • 9

Doc-to-LoRA: Learning to Instantly Internalize Contexts

Paper • 2602.15902 • Published Feb 13 • 3

upvoted a paper 21 days ago

Fast Inference from Transformers via Speculative Decoding

Paper • 2211.17192 • Published Nov 30, 2022 • 11

upvoted a paper 22 days ago

Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools

Paper • 2405.20362 • Published May 30, 2024 • 3

upvoted a collection 23 days ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 80 items • Updated 11 days ago • 485

upvoted 3 papers 23 days ago

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

Paper • 2602.21534 • Published 25 days ago • 23

Demystifying Reinforcement Learning in Agentic Reasoning

Paper • 2510.11701 • Published Oct 13, 2025 • 33

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2, 2025 • 236

upvoted a collection 23 days ago

pplx-embed

Collection

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated 24 days ago • 88

upvoted an article 23 days ago

view article

Article

Mixture of Experts (MoEs) in Transformers

• 
• 
• +5

25 days ago

•

140

upvoted a paper 28 days ago

The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies

Paper • 2602.09877 • Published Feb 10 • 197

upvoted 2 papers 29 days ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 116

BrowseComp-V^3: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

Paper • 2602.12876 • Published Feb 13 • 10