1 15 11

Yanqi Dai

YanqiDai

https://yanqidai.github.io/

AI & ML interests

Large Multimodal Models, Multi-Task Balancing, Role-Playing Agents

Recent Activity

upvoted a paper about 2 hours ago

Improvable Gap Balancing for Multi-Task Learning

commented on a paper 2 days ago

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

liked a dataset 2 days ago

YanqiDai/MathForge_NuminaMath-CoT-sample80k

View all activity

Organizations

Collections 2

Papers 4

models 2

YanqiDai/MMRole-Eval_RM

Updated Aug 29, 2024 • 4 • 1

YanqiDai/MMRole-Agent

Updated Aug 29, 2024 • 3 • 2

datasets 4

Yanqi Dai

AI & ML interests

Recent Activity

Organizations

Collections 2

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

YanqiDai/MathForge_MATH-augmented

YanqiDai/MathForge_GEOQA-R1V-revised

YanqiDai/MathForge_NuminaMath-CoT-sample80k

MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

YanqiDai/MMRole_dataset

YanqiDai/MMRole-Eval_RM

YanqiDai/MMRole-Agent

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

YanqiDai/MathForge_MATH-augmented

YanqiDai/MathForge_GEOQA-R1V-revised

YanqiDai/MathForge_NuminaMath-CoT-sample80k

MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

YanqiDai/MMRole_dataset

YanqiDai/MMRole-Eval_RM

YanqiDai/MMRole-Agent

Papers 4

models 2

YanqiDai/MMRole-Eval_RM

YanqiDai/MMRole-Agent

datasets 4

YanqiDai/MathForge_NuminaMath-CoT-sample80k

YanqiDai/MathForge_GEOQA-R1V-revised

YanqiDai/MathForge_MATH-augmented

YanqiDai/MMRole_dataset

Yanqi Dai

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 4

models 2 Sort: Recently updated

datasets 4 Sort: Recently updated

models 2

datasets 4