arxiv:2410.04717
Dylan PRO
shizhuo2
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning upvoted a paper 14 days ago
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation upvoted a paper about 1 month ago
MiniCorp: The Last Mile of the AI Agent FirmOrganizations
models 76
shizhuo2/omega-qwen3-4b-HOM-ALL-grpo-v1
4B • Updated • 5
shizhuo2/omega-qwen3-4b-HET-ALL-grpo-v1
4B • Updated • 8
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 • 2
shizhuo2/qwen3_4b_omega_48pq_div1_s16_gs439_100
2B • Updated • 4
datasets 36
shizhuo2/sokoban-diversity-trajectories
Updated • 39
shizhuo2/omega-het-expandA-raw-full
Preview • Updated • 10
shizhuo2/omega-het-expandA-sft
Viewer • Updated • 855k • 116
shizhuo2/omega-het-expandA-verified
Viewer • Updated • 394k • 25
shizhuo2/omega-het-expandA-200k-raw
Preview • Updated • 28
shizhuo2/omega-het-sft-rl-v2
Viewer • Updated • 592 • 20
shizhuo2/omega-het-sft-rl
Viewer • Updated • 155k • 17
shizhuo2/acereason_math_ge10_lexical_v2_similar_150k
Viewer • Updated • 150k • 26
shizhuo2/acereason_math_ge10_lexical_v2_similar_100k
Viewer • Updated • 100k • 20
shizhuo2/acereason_math_ge10_lexical_v2_similar_50k
Viewer • Updated • 50k • 25