yixuan's picture

In a Training Loop 🔄

yixuan PRO

yixuantt

·

yixuantt

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

upvoted a paper 4 days ago

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

commented on a paper 4 days ago

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

View all activity

Organizations

Papers 9

arxiv:2512.02807

arxiv:2509.10844

arxiv:2509.07370

arxiv:2502.10990

spaces 2

User Study

This is a demo for user study.

MultiHop RAG

Display and search multihop-RAG benchmark results

models 2

yixuantt/Qwen2.5-3B-R1-Finance

Text Generation • 3B • Updated Mar 10 • 7 • 1

yixuantt/InvestLM-mistral-AWQ

Text Generation • 6B • Updated Oct 7, 2024 • 3

datasets 4

yixuantt/sharegpt-dolly-15k

Viewer • Updated Nov 25, 2024 • 15k • 26

yixuantt/ir_data

Viewer • Updated Oct 22, 2024 • 1.39M • 14

yixuantt/MultiHopRAG

Viewer • Updated Jan 30, 2024 • 3.17k • 938 • 62

yixuantt/FinEntity

Viewer • Updated Jan 24, 2024 • 979 • 98 • 4