Zhepei Wei

weizhepei's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 datasets 1 day ago

weizhepei/TruthRL-HotpotQA

Viewer • Updated 1 day ago • 7.41k • 18

weizhepei/TruthRL-NaturalQuestions

Viewer • Updated 1 day ago • 3.61k • 17

updated a dataset 3 days ago

weizhepei/TruthRL-MuSiQue

Viewer • Updated 3 days ago • 22.4k • 18

published 3 datasets 3 days ago

weizhepei/TruthRL-NaturalQuestions

Viewer • Updated 1 day ago • 3.61k • 17

weizhepei/TruthRL-MuSiQue

Viewer • Updated 3 days ago • 22.4k • 18

weizhepei/TruthRL-HotpotQA

Viewer • Updated 1 day ago • 7.41k • 18

updated a dataset 3 days ago

weizhepei/TruthRL-CRAG

Viewer • Updated 3 days ago • 1.3k • 20

published a dataset 3 days ago

weizhepei/TruthRL-CRAG

Viewer • Updated 3 days ago • 1.3k • 20

upvoted a paper 15 days ago

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

Paper • 2510.06217 • Published 16 days ago • 61

updated a dataset 21 days ago

meng-lab/DeSA-RecallResult

Updated 21 days ago • 98

upvoted a paper 21 days ago

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

Paper • 2509.03403 • Published Sep 3 • 21

upvoted a paper 22 days ago

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Paper • 2509.25760 • Published 23 days ago • 52

commented a paper 22 days ago

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Paper • 2509.25760 • Published 23 days ago • 52 •

3

updated a model 25 days ago

meng-lab/DeSA-qwen2.5-3b-it-em-after50stepsacc-step150

3B • Updated 25 days ago • 8

published a model 25 days ago

meng-lab/DeSA-qwen2.5-3b-it-em-after50stepsacc-step150

3B • Updated 25 days ago • 8

updated a model 29 days ago

meng-lab/DeSA-qwen2.5-3b-it-stage1-acc

Updated 29 days ago

published a model 29 days ago

meng-lab/DeSA-qwen2.5-3b-it-stage1-acc

Updated 29 days ago

updated 3 models 29 days ago

meng-lab/DeSA-qwen2.5-3b-it-searchbehaviorandem

Updated 29 days ago

meng-lab/DeSA-qwen2.5-7b-it-em

Updated 29 days ago

meng-lab/DeSA-qwen2.5-7b-it-em-after100stepsrecall-clamp

Updated 29 days ago