Stella Li PRO
stellalisy
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Cognitive Foundations for Reasoning and Their Manifestation in LLMs
updated
a dataset
10 days ago
stellalisy/Dolci-RLZero-Math-7B_random
published
a dataset
10 days ago
stellalisy/Dolci-RLZero-Math-7B_random
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 • 4 -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation • 8B • Updated • 6 -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation • 8B • Updated • 24 -
stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated • 9
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 • 4 -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation • 8B • Updated • 6 -
stellalisy/rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation • 8B • Updated • 24 -
stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation • 8B • Updated • 9
models
30
stellalisy/system_select_dpo-3b-lr1e-5-b0.1
Text Generation
•
3B
•
Updated
•
2
stellalisy/system_select_dpo-3b-lr1e-6-b0.1
Text Generation
•
3B
•
Updated
•
3
stellalisy/system_select_dpo-3b-lr1e-5-b0.0
Text Generation
•
3B
•
Updated
•
2
stellalisy/system_select_dpo-1b-lr1e-6-b0.1
Text Generation
•
1B
•
Updated
•
1
stellalisy/system_select_dpo-1b-lr1e-5-b0.1
Text Generation
•
1B
•
Updated
•
2
stellalisy/system_select_dpo-1b-lr1e-6-b0.0
Text Generation
•
1B
•
Updated
•
1
stellalisy/system_select_dpo-1b-lr1e-5-b0.0
Text Generation
•
1B
•
Updated
•
1
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step150
Text Generation
•
8B
•
Updated
•
8
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step100
Text Generation
•
8B
•
Updated
•
7
stellalisy/rethink_rlvr_reproduce-incorrect-qwen2.5_math_7b-lr5e-7-kl0.00-step50
Text Generation
•
8B
•
Updated
•
8
datasets
22
stellalisy/Dolci-RLZero-Math-7B_random
Viewer
•
Updated
•
13.3k
•
34
stellalisy/PrefPalette
Viewer
•
Updated
•
2.01M
•
24
stellalisy/HorizonPref_natural_0827
Viewer
•
Updated
•
1.75k
•
4
stellalisy/DAPO-Math-14k-Processed-RLVR_random
Viewer
•
Updated
•
14.1k
•
181
stellalisy/rlvr_orz_math_57k_collected_random
Viewer
•
Updated
•
56.9k
•
47
stellalisy/personalized_simpleqa
Preview
•
Updated
•
11
stellalisy/personalized_socialiqa
Preview
•
Updated
•
9
stellalisy/personalized_scienceqa
Preview
•
Updated
•
10
stellalisy/personalized_mmlu
Preview
•
Updated
•
9
stellalisy/personalized_medqa
Preview
•
Updated
•
9