Jiashu HE

JasonTree

3 1

AI & ML interests

None yet

Recent Activity

upvoted a paper about 7 hours ago

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas

upvoted a paper 16 days ago

Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops

upvoted a paper about 1 month ago

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

View all activity

Organizations

None yet

models 16

JasonTree/Qwen2.5-3B-Instruct-SFT-GRPO-commonsense

Updated Nov 25, 2025

JasonTree/Qwen2.5-3B-Instruct-SFT-commonsense

Updated Nov 24, 2025

JasonTree/Qwen2.5-3B-Instruct-SFT-GRPO-qwendata

Updated Nov 24, 2025

JasonTree/Qwen2.5-Instruct-3B-SFT-qwendata

Updated Nov 23, 2025

JasonTree/Qwen2.5-7B-Instruct-vanilla-grpo

Updated Sep 30, 2025

JasonTree/Qwen2.5-3B-Instruct-vanilla-grpo

Updated Sep 28, 2025

JasonTree/Qwen2.5-Instruct-7B-SFT-GRPO

Updated Sep 27, 2025

JasonTree/Qwen2.5-Instruct-7B-SFT

Updated Sep 25, 2025

JasonTree/Qwen2.5-Base-3B-SFT-GRPO

Updated Sep 25, 2025

JasonTree/Qwen2.5-Base-3B-SFT

Updated Sep 24, 2025

datasets 0

None public yet