Stella Li PRO
stellalisy
AI & ML interests
None yet
Recent Activity
updated
a dataset
12 days ago
stellalisy/HorizonPref_natural_0827
published
a dataset
12 days ago
stellalisy/HorizonPref_natural_0827
upvoted
a
paper
20 days ago
Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail
At It
Organizations
Spurious Rewards: Rethinking Training Signals in RLVR
-
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation • 8B • Updated -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation • 8B • Updated • 41 -
stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated
Spurious Rewards: Rethinking Training Signals in RLVR
-
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation • 8B • Updated -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation • 8B • Updated • 41 -
stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated
models
30
stellalisy/system_select_dpo-3b-lr1e-5-b0.1
Text Generation
•
3B
•
Updated
•
6
stellalisy/system_select_dpo-3b-lr1e-6-b0.1
Text Generation
•
3B
•
Updated
•
9
stellalisy/system_select_dpo-3b-lr1e-5-b0.0
Text Generation
•
3B
•
Updated
•
4
stellalisy/system_select_dpo-1b-lr1e-6-b0.1
Text Generation
•
1B
•
Updated
•
8
stellalisy/system_select_dpo-1b-lr1e-5-b0.1
Text Generation
•
1B
•
Updated
•
7
stellalisy/system_select_dpo-1b-lr1e-6-b0.0
Text Generation
•
1B
•
Updated
•
8
stellalisy/system_select_dpo-1b-lr1e-5-b0.0
Text Generation
•
1B
•
Updated
•
8
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation
•
8B
•
Updated
•
1
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation
•
8B
•
Updated
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation
•
8B
•
Updated
datasets
20
stellalisy/HorizonPref_natural_0827
Viewer
•
Updated
•
1.75k
•
60
stellalisy/DAPO-Math-14k-Processed-RLVR_random
Viewer
•
Updated
•
14.1k
•
32
stellalisy/rlvr_orz_math_57k_collected_random
Viewer
•
Updated
•
56.9k
•
33
stellalisy/personalized_simpleqa
Preview
•
Updated
•
4
stellalisy/personalized_socialiqa
Preview
•
Updated
•
3
stellalisy/personalized_scienceqa
Preview
•
Updated
•
3
stellalisy/personalized_mmlu
Preview
•
Updated
•
3
stellalisy/personalized_medqa
Preview
•
Updated
•
7
stellalisy/personalized_commonsenseqa
Preview
•
Updated
•
3
stellalisy/personalized_mascqa
Preview
•
Updated
•
4