arxiv:2410.04717
Dylan PRO
shizhuo2
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
MiniCorp: The Last Mile of the AI Agent Firm submitted a paper 2 days ago
MiniCorp: The Last Mile of the AI Agent Firm upvoted a paper 9 days ago
Selecting Diverse SFT Traces Improves Post-RL GeneralizationOrganizations
models 76
shizhuo2/omega-qwen3-4b-HOM-ALL-grpo-v1
4B • Updated • 4
shizhuo2/omega-qwen3-4b-HET-ALL-grpo-v1
4B • Updated • 4
shizhuo2/qwen3_4b_sft_84pq
Updated
shizhuo2/qwen3_4b_sft_48pq
Updated
shizhuo2/qwen3_4b_sft_24pq
Updated
shizhuo2/qwen3_1_7b_sft_84pq
Updated
shizhuo2/qwen3_1_7b_sft_48pq
Updated
shizhuo2/qwen3_1_7b_sft_24pq
Updated
shizhuo2/qwen3_4b_omega_48pq_div1_s399_gs502_100
2B • Updated • 8
shizhuo2/qwen3_4b_omega_48pq_div1_s16_gs439_100
2B • Updated • 8
datasets 36
shizhuo2/sokoban-diversity-trajectories
Updated • 179
shizhuo2/omega-het-expandA-raw-full
Preview • Updated • 41
shizhuo2/omega-het-expandA-sft
Viewer • Updated • 855k • 46
shizhuo2/omega-het-expandA-verified
Viewer • Updated • 394k • 22
shizhuo2/omega-het-expandA-200k-raw
Preview • Updated • 177
shizhuo2/omega-het-sft-rl-v2
Viewer • Updated • 592 • 13
shizhuo2/omega-het-sft-rl
Viewer • Updated • 155k • 37
shizhuo2/acereason_math_ge10_lexical_v2_similar_150k
Viewer • Updated • 150k • 5
shizhuo2/acereason_math_ge10_lexical_v2_similar_100k
Viewer • Updated • 100k • 8
shizhuo2/acereason_math_ge10_lexical_v2_similar_50k
Viewer • Updated • 50k • 12