Eugene Oskin

eoskin's activity

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

upvoted 2 papers 5 days ago

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Paper • 2606.19704 • Published 8 days ago • 39

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 9 days ago • 135

upvoted a paper 8 days ago

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published 10 days ago • 204

upvoted an article 12 days ago

view article

Article

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

• 

nvidia

•

25 days ago

• 83

upvoted a collection 12 days ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 16 items • Updated about 3 hours ago • 131

upvoted a paper 12 days ago

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Paper • 2606.11926 • Published 16 days ago • 118

upvoted 2 papers 14 days ago

AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

Paper • 2606.07326 • Published 21 days ago • 29

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

Paper • 2606.05563 • Published 22 days ago • 53

upvoted a paper 21 days ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 25 days ago • 135

upvoted a paper 24 days ago

Mellum2 Technical Report

Paper • 2605.31268 • Published 28 days ago • 55

upvoted a collection 27 days ago

👁️ LFM2.5-VL

Collection

6 items • Updated about 1 hour ago • 45

upvoted a paper 29 days ago

Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings

Paper • 2605.22391 • Published May 21 • 39

upvoted 3 papers about 1 month ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published May 14 • 91

Self-Distilled Agentic Reinforcement Learning

Paper • 2605.15155 • Published May 14 • 115

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Paper • 1910.01108 • Published Oct 2, 2019 • 23

upvoted a collection about 1 month ago

Qwen3.6

Collection

4 items • Updated Apr 22 • 418

upvoted 3 papers about 1 month ago

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

Paper • 2605.09530 • Published May 10 • 149

Efficient Pre-Training with Token Superposition

Paper • 2605.06546 • Published May 7 • 47

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE

Paper • 2505.19645 • Published Feb 16 • 1

upvoted an article about 1 month ago

view article

Article

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

• 

RakshitAralimatti

•

Aug 8, 2025

• 36