🔄 In a Training Loop

Urro

urroxyz

95 934 103

https://urro.xyz/

urroxyz

AI & ML interests

computational linguistics major 🤖🔎🔠 i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.

Recent Activity

upvoted a paper 1 day ago

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

upvoted a paper 1 day ago

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

updated a collection 1 day ago

WTF GENIUS PAPERS

View all activity

Organizations

upvoted 2 papers 1 day ago

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 19 days ago • 93

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 5 days ago • 106

updated a collection 1 day ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 1 day ago

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

Paper • 2609.15126 • Published 9 days ago • 8

updated a collection 1 day ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 1 day ago

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

Paper • 2609.21619 • Published 5 days ago • 7

commented a paper 3 days ago

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

Paper • 2609.19499 • Published 7 days ago • 34 •

updated a collection 3 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted 3 papers 3 days ago

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

Paper • 2609.19499 • Published 7 days ago • 34

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published 8 days ago • 59

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 6 days ago • 37

updated a collection 4 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 4 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 6 days ago • 120

updated a collection 4 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 4 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 6 days ago • 105

updated a collection 4 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 4 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 6 days ago • 166

updated a collection 4 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

upvoted a paper 4 days ago

What Does Privileged Information Add to On-Policy Self-Distillation?

Paper • 2609.20612 • Published 6 days ago • 33

updated a collection 4 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 388 items • Updated 1 day ago • 86

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity