Qian Liu's picture

Qian Liu

SivilTaram

·

http://siviltaram.github.io/

AI & ML interests

Cooking cool things

Recent Activity

upvoted a paper 1 day ago

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

upvoted a paper 3 days ago

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

authored a paper 4 days ago

General-Reasoner: Advancing LLM Reasoning Across All Domains

View all activity

Organizations

SivilTaram's activity

upvoted a paper 1 day ago

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published 3 days ago • 19

upvoted a paper 3 days ago

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Paper • 2505.15612 • Published 3 days ago • 28

upvoted a paper 4 days ago

General-Reasoner: Advancing LLM Reasoning Across All Domains

Paper • 2505.14652 • Published 4 days ago • 17

upvoted a paper 5 days ago

Group-in-Group Policy Optimization for LLM Agent Training

Paper • 2505.10978 • Published 9 days ago • 3

upvoted 2 papers 6 days ago

Qwen3 Technical Report

Paper • 2505.09388 • Published 11 days ago • 147

Parallel Scaling Law for Language Models

Paper • 2505.10475 • Published 9 days ago • 73

upvoted a paper 19 days ago

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Paper • 2505.02735 • Published 19 days ago • 31

upvoted a paper about 1 month ago

CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Paper • 2504.13161 • Published Apr 17 • 92

upvoted 2 papers about 2 months ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published Mar 30 • 133

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

Paper • 2503.00808 • Published Mar 2 • 57

upvoted a collection 2 months ago

SimpleRL-Zoo

The collection for the Paper "SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild" • 13 items • Updated 20 days ago • 6

upvoted 2 papers 2 months ago

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Paper • 2503.18892 • Published Mar 24 • 30

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

Paper • 2503.15450 • Published Mar 19 • 11

upvoted a collection 3 months ago

PreSelect

3 items • Updated 20 days ago • 1

upvoted an article 3 months ago

Article

DualPipe could be better without the Dual

By

•

Feb 28

• 17

upvoted 3 papers 3 months ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 103

Craw4LLM: Efficient Web Crawling for LLM Pretraining

Paper • 2502.13347 • Published Feb 19 • 28

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Paper • 2502.12982 • Published Feb 18 • 17

upvoted a collection 3 months ago

SimpleRL

The collection for the Project "Simple Reinforcement Learning for Reasoning" • 2 items • Updated Feb 19 • 7

upvoted a paper 3 months ago

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published Feb 3 • 70