arxiv:2504.11343
Maxwell Yao
MaxwellJryao
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 12 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
upvoted
a
paper
3 months ago
GAR: Generative Adversarial Reinforcement Learning for Formal Theorem
Proving
upvoted
a
paper
7 months ago
Chain-of-Experts: Unlocking the Communication Power of
Mixture-of-Experts Models
Organizations
models
35
MaxwellJryao/sft_loraMoE_-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_loraMoE_wiki_hop_original_choose_best_object_affirmative_1-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_wiki_hop_original_choose_best_object_affirmative_1-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_race_high_Select_the_best_answer-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_openbookqa_main_pick_using_id-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_imdb_Reviewer_Opinion_bad_good_choices-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_super_glue_boolq_yes_no_question-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
•
1
MaxwellJryao/sft_piqa_pick_correct_choice_index-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
•
2
MaxwellJryao/sft_sciq_Multiple_Choice-lora-sft_Qwen2-1.5B_lr-1e-3
Updated
MaxwellJryao/sft_ai2_arc_ARC_Challenge_pick_the_most_correct_option-lora-sft_Qwen2-1.5B_lr-1e-3
Updated