🔄 In a Training Loop

Urro

urroxyz

89 758 100

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 3 hours ago

WTF GENIUS PAPERS

updated a collection about 3 hours ago

WTF GENIUS PAPERS

upvoted a paper about 3 hours ago

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

View all activity

Organizations

updated a collection about 3 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 3 hours ago

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Paper • 2607.25675 • Published 3 days ago • 54

updated a collection about 3 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 3 hours ago

CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation

Paper • 2607.16955 • Published 13 days ago • 4

updated a collection about 3 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 3 hours ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 3 days ago • 73

updated a collection about 23 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 23 hours ago

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Paper • 2607.25431 • Published 3 days ago • 73

updated a collection about 23 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 23 hours ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published 3 days ago • 28

updated a collection about 23 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper about 23 hours ago

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

Paper • 2607.25091 • Published 4 days ago • 5

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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper 2 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 4 days ago • 386

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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper 2 days ago

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

Paper • 2607.22098 • Published 7 days ago • 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. • 237 items • Updated about 3 hours ago • 55

upvoted a paper 2 days ago

Codifying the Judge: Scalable Evaluation via Program Distillation

Paper • 2607.22561 • Published May 29 • 8

liked a model 5 days ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated 2 days ago • 24.5k • 581

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity