-
rulins/rl_rag_longform_rubrics_only_with_system_prompt
Viewer • Updated • 1k • 105 -
rulins/rl_rag_surveyqa_validation_longform_rubrics_only_with_system_prompt
Viewer • Updated • 703 • 29 -
rulins/rl_rag_surveyqa_validation_longform_averaged_outcome_with_system_prompt
Viewer • Updated • 703 • 99
Rulin Shao
rulins
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 1 hour ago
rl-rag/rl_rag_sqa_searcharena_rubrics_web_augmented_rubrics_only_call_tool
published
a dataset
about 1 hour ago
rl-rag/rl_rag_sqa_searcharena_rubrics_web_augmented_rubrics_only_call_tool
updated
a model
3 days ago
rl-rag/qwen3-8b-base-combined-sft-training-data-v20250824_MiroSystemPrompt
Organizations
-
rulins/math-llama31-8b-n64-filtered
Viewer • Updated • 20 • 11 -
rulins/5math-qwen-math-n64-mv-filtered-10each
Viewer • Updated • 40 • 7 -
rulins/5math-5assessors-n64-filtered-20each
Viewer • Updated • 80 • 20 -
rulins/math-qwen25-math-7b-n64-filtered-10each
Viewer • Updated • 40 • 22
-
rulins/rl_rag_longform_rubrics_only_with_system_prompt
Viewer • Updated • 1k • 105 -
rulins/rl_rag_surveyqa_validation_longform_rubrics_only_with_system_prompt
Viewer • Updated • 703 • 29 -
rulins/rl_rag_surveyqa_validation_longform_averaged_outcome_with_system_prompt
Viewer • Updated • 703 • 99
-
rulins/math-llama31-8b-n64-filtered
Viewer • Updated • 20 • 11 -
rulins/5math-qwen-math-n64-mv-filtered-10each
Viewer • Updated • 40 • 7 -
rulins/5math-5assessors-n64-filtered-20each
Viewer • Updated • 80 • 20 -
rulins/math-qwen25-math-7b-n64-filtered-10each
Viewer • Updated • 40 • 22
models
5
rulins/250717_scholarqabench_with_gt_rlvr_with_system_prompt_qwq_rm_step500
8B
•
Updated
•
7
rulins/250717_rl_rag_longform_rubrics_only_with_system_prompt_qwq_rm_step_400
8B
•
Updated
•
11
rulins/rl-rag-sqa-dev-reason-rm-gpt4omini
8B
•
Updated
•
11
rulins/pes2o-v3-id-mapping
Updated
rulins/blip2-t5-llava
Image-Text-to-Text
•
Updated
•
3
datasets
100
rulins/rl_rag_no_retrieval_1k_longform_rubrics_only_with_system_prompt
Viewer
•
Updated
•
999
•
66
rulins/rl_rag_sqa_no_retrieval_1k_longform_averaged_outcome_with_system_prompt
Viewer
•
Updated
•
999
•
59
rulins/rl_rag_sqa_no_retrieval_1k_longform_finegrained_with_system_prompt
Viewer
•
Updated
•
999
•
64
rulins/multi_question_synthetic_single_source_2wiki_15q
Viewer
•
Updated
•
1.02k
•
75
rulins/multi_question_synthetic_single_source_2wiki_10q
Viewer
•
Updated
•
1.53k
•
71
rulins/multi_question_synthetic_single_source_tqa_15q
Viewer
•
Updated
•
10.4k
•
64
rulins/multi_question_synthetic_single_source_tqa_10q
Viewer
•
Updated
•
15.6k
•
66
rulins/multi_question_synthetic_single_source_2wiki_5q
Viewer
•
Updated
•
3.06k
•
88
rulins/multi_question_synthetic_single_source_2wiki_2q
Viewer
•
Updated
•
7.65k
•
89
rulins/multi_question_synthetic_single_source_tqa_5q
Viewer
•
Updated
•
31.2k
•
112