🔄 In a Training Loop

Urro

urroxyz

89 744 98

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

updated a collection about 20 hours ago

WTF GENIUS PAPERS

upvoted a paper about 20 hours ago

AutoIndex: Learning Representation Programs for Retrieval

updated a collection about 20 hours ago

WTF GENIUS PAPERS

View all activity

Organizations

updated a collection about 20 hours 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper about 20 hours ago

AutoIndex: Learning Representation Programs for Retrieval

Paper • 2607.18603 • Published 4 days ago • 9

updated a collection about 20 hours 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper about 20 hours ago

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

Paper • 2607.20379 • Published 3 days ago • 4

updated a collection about 20 hours 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper about 20 hours ago

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Paper • 2607.10169 • Published 14 days ago • 12

updated a collection about 20 hours 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper about 20 hours ago

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

Paper • 2607.19604 • Published 4 days ago • 13

updated a collection about 20 hours 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper about 20 hours ago

SLPO: Scaling Latent Reasoning via a Surrogate Policy

Paper • 2607.19691 • Published 3 days ago • 4

commented a paper 1 day ago

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

Paper • 2509.24945 • Published Sep 29, 2025 • 7 •

upvoted a paper 1 day ago

Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation

Paper • 2605.29502 • Published May 28 • 1

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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper 1 day ago

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

Paper • 2509.24945 • Published Sep 29, 2025 • 7

updated a collection 2 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. • 223 items • Updated about 20 hours ago • 50

upvoted a paper 2 days ago

Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training

Paper • 2607.19058 • Published 4 days ago • 6

updated a collection 2 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. • 223 items • Updated about 20 hours ago • 50

upvoted 2 papers 2 days ago

H^2SD: Hybrid Hindsight Self-Distillation

Paper • 2607.18955 • Published 4 days ago • 6

ISO: An RLVR-Native Optimization Stack

Paper • 2607.19331 • Published 3 days ago • 7

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. • 223 items • Updated about 20 hours ago • 50

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity