In a Training Loop 🔄

Urro PRO

urroxyz

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 about 17 hours ago

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?

upvoted a paper about 17 hours ago

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

updated a collection about 17 hours ago

WTF GENIUS PAPERS

View all activity

Organizations

upvoted 2 papers about 17 hours ago

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?

Paper • 2605.09591 • Published 5 days ago • 1

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

Paper • 2605.08737 • Published 6 days ago • 2

updated a collection about 17 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. • 132 items • Updated about 17 hours ago • 20

upvoted a paper about 17 hours ago

FeatCal: Feature Calibration for Post-Merging Models

Paper • 2605.13030 • Published 2 days ago • 4

updated a collection about 17 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. • 132 items • Updated about 17 hours ago • 20

commented a paper about 17 hours ago

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Paper • 2605.12825 • Published 3 days ago • 7 •

upvoted 3 papers about 17 hours ago

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. • 132 items • Updated about 17 hours ago • 20

commented a paper 1 day ago

Reliable Chain-of-Thought via Prefix Consistency

Paper • 2605.07654 • Published 7 days ago • 1 •

upvoted 3 papers 1 day ago

Reliable Chain-of-Thought via Prefix Consistency

Paper • 2605.07654 • Published 7 days ago • 1

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

Paper • 2605.05630 • Published 3 days ago • 10

Debiased Model-based Representations for Sample-efficient Continuous Control

Paper • 2605.11711 • Published 3 days ago • 8

commented a paper 1 day ago

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Paper • 2605.12460 • Published 3 days ago • 15 •

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. • 132 items • Updated about 17 hours ago • 20

upvoted 2 papers 1 day ago

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Paper • 2605.12460 • Published 3 days ago • 15

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Paper • 2605.10977 • Published 6 days ago • 9

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. • 132 items • Updated about 17 hours ago • 20

commented a paper 1 day ago

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Paper • 2605.10977 • Published 6 days ago • 9 •

Urro PRO

AI & ML interests

Recent Activity

Organizations

urroxyz's activity