1 20 14

Le Yu

vanillaOVO

https://yule-buaa.github.io/

yule-BUAA

AI & ML interests

None yet

Recent Activity

upvoted a paper about 2 hours ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

upvoted a paper about 24 hours ago

Reinforcement Pre-Training

authored a paper 7 days ago

Qwen3 Technical Report

View all activity

Organizations

None yet

vanillaOVO's activity

upvoted a paper about 2 hours ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 403

upvoted a paper about 24 hours ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published 1 day ago • 156

upvoted a paper 8 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 8 days ago • 146

upvoted a paper 23 days ago

Qwen3 Technical Report

Paper • 2505.09388 • Published 28 days ago • 188

upvoted a paper 26 days ago

WorldPM: Scaling Human Preference Modeling

Paper • 2505.10527 • Published 26 days ago • 33

upvoted an article 4 months ago

Article

Putting RL back in RLHF

and 1 other •

Jun 12, 2024

• 93

upvoted a paper 5 months ago

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

Paper • 2501.01257 • Published Jan 2 • 53

upvoted a paper 6 months ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 368

upvoted a paper 8 months ago

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models

Paper • 2410.13841 • Published Oct 17, 2024 • 17

upvoted a collection 11 months ago

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Dec 6, 2024 • 673

upvoted an article 11 months ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

and 7 others •

Jul 23, 2024

• 234

upvoted a collection about 1 year ago

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Apr 28 • 365

upvoted 2 articles about 1 year ago

Article

Fine-tune Llama 3 with ORPO

•

Apr 22, 2024

• 237

Article

Merge Large Language Models with mergekit

•

Jan 9, 2024

• 120

upvoted 3 papers over 1 year ago

upvoted a collection over 1 year ago

Papers about model merging

Collection

referenced in the mergekit repo: https://github.com/cg123/mergekit • 4 items • Updated Feb 13, 2024 • 14

upvoted 2 papers over 1 year ago

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

Paper • 2401.12474 • Published Jan 23, 2024 • 37

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 28