10 27 11

Wei Liu

PeterV09

https://vpeterv.github.io

AI & ML interests

Machine Learning, Natural Language Processing

Recent Activity

upvoted a paper about 1 hour ago

START: Self-taught Reasoner with Tools

upvoted a paper 2 days ago

Language Models can Self-Improve at State-Value Estimation for Better Search

upvoted a paper 3 days ago

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

View all activity

Organizations

PeterV09's activity

upvoted a paper about 1 hour ago

START: Self-taught Reasoner with Tools

Paper • 2503.04625 • Published about 15 hours ago • 29

upvoted a paper 2 days ago

Language Models can Self-Improve at State-Value Estimation for Better Search

Paper • 2503.02878 • Published 3 days ago • 7

upvoted a paper 3 days ago

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

Paper • 2503.00808 • Published 5 days ago • 51

upvoted a paper 15 days ago

MoM: Linear Sequence Modeling with Mixture-of-Memories

Paper • 2502.13685 • Published 16 days ago • 33

upvoted a paper 22 days ago

LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid

Paper • 2502.07563 • Published 24 days ago • 24

upvoted a paper 23 days ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 24 days ago • 46

upvoted a paper about 1 month ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22 • 56

upvoted 4 papers about 2 months ago

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published Jan 7 • 43

Cosmos World Foundation Model Platform for Physical AI

Paper • 2501.03575 • Published Jan 7 • 69

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Paper • 2501.03262 • Published Jan 4 • 92

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Paper • 2501.03124 • Published Jan 6 • 14

upvoted 3 papers 2 months ago

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published Dec 27, 2024 • 82

Diving into Self-Evolving Training for Multimodal Reasoning

Paper • 2412.17451 • Published Dec 23, 2024 • 43

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Paper • 2412.17256 • Published Dec 23, 2024 • 46

upvoted 2 papers 5 months ago

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

Paper • 2409.19291 • Published Sep 28, 2024 • 19

Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale

Paper • 2409.17115 • Published Sep 25, 2024 • 62

upvoted a paper 6 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19, 2024 • 137

upvoted an article 8 months ago

Article

How NuminaMath Won the 1st AIMO Progress Prize

Jul 11, 2024

• 118

upvoted 2 papers 8 months ago

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs

Paper • 2407.10058 • Published Jul 14, 2024 • 31

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

Paper • 2407.08733 • Published Jul 11, 2024 • 23