🤝 Open to Collab

Urro

urroxyz

107 1106 111

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 2 days ago

Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

upvoted a paper 2 days ago

SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

updated a collection 2 days ago

WTF GENIUS PAPERS

View all activity

Organizations

upvoted 2 papers 2 days ago

Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

Paper • 2608.22237 • Published 8 days ago • 22

SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

Paper • 2611.13410 • Published 5 days ago • 37

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 2 days ago

Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

Paper • 2610.39671 • Published 17 days ago • 36

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 2 days ago

Scaling Mathematical Proof Supervision from Structured Textbooks

Paper • 2610.40394 • Published 17 days ago • 48

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 2 days ago

Memorilla: Latent Semantic Memory for LLMs

Paper • 2610.21375 • Published about 1 month ago • 2

updated a collection 3 days ago

HUMAN-WRITTEN & LEGALLY-SOURCED*

Collection

Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. • 172 items • Updated 3 days ago • 10

liked a dataset 3 days ago

p-doom/AGI-CAST-0.6k

Updated Mar 20 • 2.01k • 25

updated a collection 3 days ago

HUMAN-WRITTEN & LEGALLY-SOURCED*

Collection

Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. • 172 items • Updated 3 days ago • 10

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 4 days ago

Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters

Paper • 2611.09634 • Published 9 days ago • 12

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 4 days ago

LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time

Paper • 2611.07025 • Published 10 days ago • 37

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. • 533 items • Updated 2 days ago • 111

upvoted a paper 4 days ago

How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?

Paper • 2611.11450 • Published 7 days ago • 14

updated a collection 5 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. • 533 items • Updated 2 days ago • 111

upvoted a paper 5 days ago

Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription

Paper • 2611.06043 • Published 11 days ago • 94

updated a collection 5 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. • 533 items • Updated 2 days ago • 111

Urro

AI & ML interests

Recent Activity

Organizations

urroxyz's activity