Joel Wang

joelhenwang's activity

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

liked a model 1 day ago

LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF

Text Generation • 0.3B • Updated 3 days ago • 1.53k • 26

liked 3 models 2 days ago

ornith-ai/Ornith-1.5-9B

Text Generation • 10B • Updated about 23 hours ago • 31.5k • • 187

empero-ai/Qwen3.8-9B-Distill

Text Generation • 10B • Updated 8 days ago • 10.5k • • 170

ornith-ai/Ornith-1.5-35B-A3B

Text Generation • 36B • Updated 1 day ago • 23.5k • 370

liked 2 models 3 days ago

incoai/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated 5 days ago • 69.8k • 165

z-lab/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated 5 days ago • 36.2k • 206

upvoted 11 papers 5 days ago

A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization

Paper • 2608.08156 • Published 16 days ago • 10

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Paper • 2608.11079 • Published 13 days ago • 17

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop

Paper • 2608.11215 • Published Jul 19 • 6

Self-Evolving Embodied Agents via Skill-Harness Evolution

Paper • 2608.11350 • Published 13 days ago • 13

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Paper • 2608.12307 • Published 12 days ago • 113

Thought-Level Beam Search for Reasoning

Paper • 2608.08020 • Published 13 days ago • 15

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

Paper • 2608.10538 • Published 13 days ago • 15

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 11 days ago • 54

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

Paper • 2608.14905 • Published 10 days ago • 29

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

Paper • 2608.16393 • Published 6 days ago • 6

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Paper • 2608.17800 • Published 6 days ago • 9

liked 3 models 6 days ago

vectionlabs/Salience-27B-R5

Image-Text-to-Text • 28B • Updated 4 days ago • 454 • 30

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 10 days ago • 2.36M • • 12.4k

TeichAI/Qwen3.8-27B-Fable-Distill

Image-Text-to-Text • 28B • Updated 7 days ago • 1.29k • • 35