Urro

urroxyz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 8 papers about 9 hours ago

Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published 2 days ago • 76

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Paper • 2601.22146 • Published 1 day ago • 4

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

Paper • 2601.20829 • Published 2 days ago • 5

VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning

Paper • 2601.20055 • Published 3 days ago • 6

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Paper • 2601.20209 • Published 3 days ago • 19

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published 2 days ago • 20

EvolVE: Evolutionary Search for LLM-based Verilog Generation and Optimization

Paper • 2601.18067 • Published 5 days ago • 4

Self-Distillation Enables Continual Learning

Paper • 2601.19897 • Published 3 days ago • 18

liked a dataset about 10 hours ago

trl-lib/math_shepherd

Viewer • Updated Jan 8, 2025 • 445k • 2.6k • 11

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 on tiny models (AR & dLLMs). • 38 items • Updated 2 days ago • 1

upvoted a paper 2 days ago

The Surprising Effectiveness of Test-Time Training for Abstract Reasoning

Paper • 2411.07279 • Published Nov 11, 2024 • 4

liked a model 3 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • Updated about 2 hours ago • 25.4k • • 1.2k

upvoted a paper 3 days ago

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

Paper • 2504.18225 • Published Apr 25, 2025 • 15

liked a dataset 3 days ago

osunlp/Mind2Web

Viewer • Updated Oct 19, 2025 • 253 • 1.87k • 120

updated 2 collections 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. • 118 items • Updated 3 days ago • 1

TINY MODELS WITH BIG INTELLIGENCE

Collection

Tiny (<30B) models that tend to outperform their same-parameter counterparts. • 10 items • Updated 3 days ago • 1

upvoted 2 papers 3 days ago

Mind2Web: Towards a Generalist Agent for the Web

Paper • 2306.06070 • Published Jun 9, 2023 • 20

Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models

Paper • 2512.06266 • Published Dec 6, 2025 • 5

liked a model 3 days ago

janhq/Jan-v3-4B-base-instruct

Text Generation • 4B • Updated 3 days ago • 288 • 33

upvoted a paper 3 days ago

Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

Paper • 2601.17058 • Published 9 days ago • 176