🔄 In a Training Loop

Urro

urroxyz

94 842 101

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

MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline

upvoted a paper 1 day ago

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

upvoted a paper 1 day ago

rStar2-Agent: Agentic Reasoning Technical Report

View all activity

Organizations

upvoted 3 papers 1 day ago

MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline

Paper • 2510.07307 • Published Oct 8, 2025 • 7

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published Jun 29 • 104

rStar2-Agent: Agentic Reasoning Technical Report

Paper • 2508.20722 • Published Aug 28, 2025 • 121

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. • 299 items • Updated 1 day ago • 69

upvoted 2 papers 1 day ago

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

Paper • 2508.16949 • Published Aug 23, 2025 • 25

Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics

Paper • 2603.01209 • Published Mar 1 • 2

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. • 299 items • Updated 1 day ago • 69

upvoted 3 papers 2 days ago

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

Paper • 2608.19758 • Published 4 days ago • 16

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Paper • 2608.18580 • Published 5 days ago • 114

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Paper • 2608.20281 • Published 4 days ago • 10

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. • 299 items • Updated 1 day ago • 69

upvoted 2 papers 2 days ago

LLMs Get Smarter from Targeted Synthetic Multilingual Data

Paper • 2608.15964 • Published 8 days ago • 4

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 4 days ago • 254

commented a paper 2 days ago

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

Paper • 2608.17744 • Published 5 days ago • 13 •

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. • 299 items • Updated 1 day ago • 69

upvoted a paper 2 days ago

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

Paper • 2608.17744 • Published 5 days ago • 13

upvoted a paper 3 days ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 7 days ago • 80

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. • 299 items • Updated 1 day ago • 69

upvoted 2 papers 3 days ago

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement

Paper • 2608.14221 • Published 9 days ago • 8

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published 5 days ago • 48

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity