Jerry Huang's picture

3 1

Jerry Huang PRO

jerry128

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

updated a dataset 2 months ago

jerry128/rag-rl-sft-linear

updated a dataset 2 months ago

jerry128/rag-rl-sft-min-max

View all activity

Organizations

jerry128 's datasets 149

jerry128/RAG-RL-2Wiki-Eval-50k

Viewer • Updated Apr 2 • 12.6k • 4

jerry128/RAG-RL-MuSiQue-Eval-50k

Viewer • Updated Apr 2 • 2.42k

jerry128/RAG-RL-HotpotQA-Eval-50k

Viewer • Updated Apr 2 • 7.41k • 22

jerry128/RAG-RL-2Wiki-Min-Max-Shuffled

Viewer • Updated Mar 31 • 5k • 2

jerry128/RAG-RL-2Wiki-Min-Max

Viewer • Updated Mar 31 • 5k • 2

jerry128/RAG-RL-2Wiki-Linear-Shuffled

Viewer • Updated Mar 31 • 5k • 1

jerry128/RAG-RL-2Wiki-Linear

Viewer • Updated Mar 31 • 5k • 5

jerry128/RAG-RL-2Wiki-Max

Updated Mar 31 • 1

jerry128/RAG-RL-MuSiQue-Min-Max-Shuffled

Viewer • Updated Mar 31 • 5k • 3

jerry128/RAG-RL-MuSiQue-Min-Max

Viewer • Updated Mar 31 • 5k • 1

jerry128/RAG-RL-MuSiQue-Linear-Sorted-by-Num-Hops

Viewer • Updated Mar 31 • 5k • 4

jerry128/RAG-RL-MuSiQue-Linear-Shuffled

Viewer • Updated Mar 31 • 5k • 1

jerry128/RAG-RL-MuSiQue-Linear

Viewer • Updated Mar 31 • 5k • 2

jerry128/RAG-RL-MuSiQue-Max

Viewer • Updated Mar 31 • 5k • 1

jerry128/RAG-RL-HotpotQA-Min-Max-Shuffled

Viewer • Updated Mar 31 • 5k • 2

jerry128/RAG-RL-HotpotQA-Min-Max

Viewer • Updated Mar 31 • 5k • 1

jerry128/RAG-RL-HotpotQA-Linear-Shuffled

Preview • Updated Mar 31 • 1

jerry128/RAG-RL-HotpotQA-Linear

Viewer • Updated Mar 31 • 5k • 2

jerry128/RAG-RL-HotpotQA-Max

Viewer • Updated Mar 31 • 5k • 4

jerry128/RAG-RL-2Wiki-OOD

Viewer • Updated Mar 30 • 4.47k • 3

jerry128/RAG-RL-2Wiki-ID

Viewer • Updated Mar 30 • 4.47k • 3

jerry128/RAG-RL-HotpotQA-OOD

Viewer • Updated Mar 30 • 3.99k • 1

jerry128/RAG-RL-HotpotQA-ID

Viewer • Updated Mar 30 • 3.99k • 3

jerry128/RAG-RL-MuSiQue-OOD

Viewer • Updated Mar 30 • 4.06k • 2

jerry128/RAG-RL-MuSiQue-ID

Viewer • Updated Mar 30 • 4.06k • 2

jerry128/RAG-RL-MuSiQue-Max-50k

Viewer • Updated Mar 30 • 19.9k • 2

jerry128/RAG-RL-2Wiki-Max-50k

Viewer • Updated Mar 29 • 50k • 3

jerry128/RAG-RL-HotpotQA-Max-50k

Viewer • Updated Mar 29 • 50k • 3

jerry128/Rank-RL-Eval2

Viewer • Updated Mar 24 • 100 • 2

jerry128/Rank-RL-Train-2-ms_macro

Viewer • Updated Mar 24 • 25k • 2