🔄 In a Training Loop

Urro

urroxyz

89 749 99

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

liked a model about 18 hours ago

Nanbeige/Nanbeige4.2-3B

upvoted a paper about 22 hours ago

Sample-Efficient Learning from Agent Experience

updated a collection 2 days ago

WTF GENIUS PAPERS

View all activity

Organizations

liked a model about 18 hours ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated about 12 hours ago • 14k • 443

upvoted a paper about 22 hours ago

Sample-Efficient Learning from Agent Experience

Paper • 2607.21051 • Published 4 days ago • 12

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 2 days ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published 5 days ago • 29

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 2 days ago

Predictive Divergence Masks for LLM RL

Paper • 2607.10848 • Published 15 days ago • 9

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 2 days ago

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

Paper • 2605.09635 • Published 4 days ago • 57

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 2 days ago

Multi-Turn On-Policy Distillation with Prefix Replay

Paper • 2607.04763 • Published 11 days ago • 9

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 3 days ago

AutoIndex: Learning Representation Programs for Retrieval

Paper • 2607.18603 • Published 6 days ago • 9

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 3 days ago

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

Paper • 2607.20379 • Published 5 days ago • 5

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 3 days ago

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

Paper • 2607.10169 • Published 16 days ago • 13

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 3 days ago

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

Paper • 2607.19604 • Published 6 days ago • 16

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. • 227 items • Updated 2 days ago • 51

upvoted a paper 3 days ago

SLPO: Scaling Latent Reasoning via a Surrogate Policy

Paper • 2607.19691 • Published 5 days ago • 5

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity