Building on HF

3 9 14

frank W.H.

securerat

https://github.com/backrat13

AI & ML interests

Simulations and red-teaming. Breaking shit and building it up again

Recent Activity

upvoted a paper 8 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

upvoted a paper 8 days ago

SkillOS: Learning Skill Curation for Self-Evolving Agents

upvoted a paper 15 days ago

Co-Evolving Policy Distillation

View all activity

Organizations

None yet

upvoted 2 papers 8 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 15 days ago • 107

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published 11 days ago • 42

upvoted a paper 15 days ago

Co-Evolving Policy Distillation

Paper • 2604.27083 • Published 19 days ago • 64

upvoted a paper 24 days ago

A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

Paper • 2604.19572 • Published 27 days ago • 22

upvoted a changelog 24 days ago

Hugging Face Changelog

Spaces agents.md for your coding agents

about 1 month ago

• 284

upvoted an article 27 days ago

Article

OVHcloud on Hugging Face Inference Providers 🔥

OVHcloud

•

Nov 24, 2025

• 78

upvoted 2 papers over 1 year ago

LongGenBench: Long-context Generation Benchmark

Paper • 2410.04199 • Published Oct 5, 2024 • 22

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

Paper • 2410.02743 • Published Oct 3, 2024 • 7