🔄 In a Training Loop

Urro

urroxyz

82 691 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

liked a dataset about 11 hours ago

kernelmachine/open-license-corpus

upvoted a paper about 13 hours ago

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

updated a collection about 13 hours ago

WTF GENIUS PAPERS

View all activity

Organizations

liked a dataset about 11 hours ago

kernelmachine/open-license-corpus

Viewer • Updated Aug 9, 2023 • 85.4M • 1.12k • 19

upvoted a paper about 13 hours ago

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

Paper • 2607.00152 • Published 5 days ago • 5

updated a collection about 13 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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper about 13 hours ago

WARP: Weight-Space Analysis for Recovering Training Data Portfolios

Paper • 2607.01686 • Published 3 days ago • 5

updated a collection about 13 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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper about 13 hours ago

Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Paper • 2607.01763 • Published 3 days ago • 5

updated a collection about 13 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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper about 13 hours ago

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

Paper • 2606.29961 • Published 6 days ago • 5

updated a collection about 13 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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper about 13 hours ago

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 6 days ago • 37

upvoted a paper 4 days ago

ReFreeKV: Towards Threshold-Free KV Cache Compression

Paper • 2502.16886 • Published 9 days ago • 47

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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper 4 days ago

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

Paper • 2606.31315 • Published 5 days ago • 73

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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper 4 days ago

Multi-Block Diffusion Language Models

Paper • 2606.29215 • Published 5 days ago • 32

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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper 4 days ago

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Paper • 2606.32032 • Published 5 days ago • 22

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. • 191 items • Updated about 13 hours ago • 46

upvoted a paper 4 days ago

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published 12 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. • 191 items • Updated about 13 hours ago • 46

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity