Eugene Oskin

eoskin's activity

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

upvoted a collection about 2 hours ago

MOSS-Audio

Collection

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 12 items • Updated 3 days ago • 67

upvoted 2 papers 12 days ago

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

Paper • 2606.24551 • Published 18 days ago • 28

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Paper • 2606.18394 • Published 15 days ago • 35

upvoted a collection 12 days ago

Qwen-AgentWorld

Collection

3 items • Updated 16 days ago • 66

upvoted a paper 12 days ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published 17 days ago • 146

upvoted 2 papers 19 days ago

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

Paper • 2606.19704 • Published 22 days ago • 41

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

Paper • 2606.19195 • Published 23 days ago • 139

upvoted a paper 22 days ago

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

Paper • 2606.18023 • Published 24 days ago • 209

upvoted an article 26 days ago

view article

Article

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

• 

nvidia

•

Jun 1

• 85

upvoted a collection 26 days ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 21 items • Updated about 3 hours ago • 143

upvoted a paper 26 days ago

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Paper • 2606.11926 • Published about 1 month ago • 126

upvoted 2 papers 28 days ago

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

Paper • 2606.07326 • Published Jun 5 • 29

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

Paper • 2606.05563 • Published Jun 4 • 55

upvoted 2 papers about 1 month ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 140

Mellum2 Technical Report

Paper • 2605.31268 • Published May 29 • 58

upvoted a collection about 1 month ago

👁️ LFM2.5-VL

Collection

6 items • Updated 14 days ago • 46

upvoted a paper about 1 month ago

Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings

Paper • 2605.22391 • Published May 21 • 41

upvoted 3 papers about 2 months 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 • 116

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

Paper • 1910.01108 • Published Oct 2, 2019 • 23