🤝 Open to Collab

Urro

urroxyz

99 1009 109

P(doom) Rejects the premise

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 about 15 hours ago

Recursive Self-Improvement through Multi-Agent Self-Supervision

commentedon a paper about 15 hours ago

Recursive Self-Improvement through Multi-Agent Self-Supervision

upvoted a paper 1 day ago

REMORY: Learning Residual Memory for Context Compaction

View all activity

Organizations

upvoted a paper about 15 hours ago

Recursive Self-Improvement through Multi-Agent Self-Supervision

Paper • 2610.12176 • Published 5 days ago • 3

commented a paper about 15 hours ago

Recursive Self-Improvement through Multi-Agent Self-Supervision

Paper • 2610.12176 • Published 5 days ago • 3 •

upvoted a paper 1 day ago

REMORY: Learning Residual Memory for Context Compaction

Paper • 2610.11287 • Published 5 days ago • 50

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 1 day ago

Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors

Paper • 2609.34344 • Published 15 days ago • 5

liked a model 3 days ago

smulelabs/Smule-Renaissance-Small

Updated Oct 27, 2025 • 9

liked a dataset 3 days ago

espnet/yodas3

Viewer • Updated 5 days ago • 4.08M • 267k • 235

commented on YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research 3 days ago

Thank you guys so much.

upvoted an article 3 days ago

Article

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

espnet

•

15 days ago

• 36

upvoted a changelog 4 days ago

Hugging Face Changelog

P(doom) on user profiles

7 days ago

• 343

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 4 days ago

Minimal Witness Reinforcement Learning

Paper • 2610.07226 • Published 8 days ago • 21

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 4 days ago

EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory

Paper • 2610.10533 • Published 6 days ago • 7

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 4 days ago

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 14 days ago • 124

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 4 days ago

Recurrent Looped Transformer

Paper • 2610.07591 • Published 7 days ago • 29

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. • 454 items • Updated 1 day ago • 99

upvoted a paper 4 days ago

Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective

Paper • 2610.03185 • Published 11 days ago • 30

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

P(doom) on user profiles