Agentic Auto-Research is Fuzz Testing
Paper • 2608.09855 • Published • 7
🏝️ On Vacation
Amber
AmberLJC
AI & ML interests
AI4S, LLM Systems
Recent Activity
updated a model about 4 hours ago
AgentNativeResearchLab/qwen3.8-27b-full13 published a model about 4 hours ago
AgentNativeResearchLab/qwen3.8-27b-full13 liked a dataset 12 days ago
nvidia/SWE-Zero-openhands-trajectoriesOrganizations
upvoted a paper about 1 month ago
upvoted an article about 2 months ago
Article
What We Learned by Reproducing 2,200 papers from ICML
abidlabs
• • 118 upvoted a paper 4 months ago
upvoted a paper 5 months ago
upvoted an article 8 months ago
Article
Why Coding Agents Can’t Replace ML Systems Engineers (Yet)
AmberLJC
• • 2 upvoted a paper 9 months ago
upvoted 4
articles 9 months ago
Article
How I manage to vibe fine-tuning LLMs as a Physics PhD
AmberLJC
• • 3 Article
Build AI Co-Scientists That Actually Help
AmberLJC
• • 1 Article
When LLMs Grow Hands and Feet, How to Design our Agentic RL Systems?
AmberLJC
• • 1 Article
Agent-Oriented Compute: My Agent can Run GPU experiments for my AI research!
AmberLJC
• • 1 upvoted an article 10 months ago
Article
Claude now can do AI Research Experiments with this AI Research Engineering SKILLS
AmberLJC
• • 6 upvoted 3
papers over 1 year ago
The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
Paper • 2505.06371 • Published • 1
EXP-Bench: Can AI Conduct AI Research Experiments?
Paper • 2505.24785 • Published • 24
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Paper • 2502.16069 • Published • 20