Zhan Cheng

zcheng256's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 15 hours ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-1.5B-LoRA

Updated about 7 hours ago

published a model about 15 hours ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-1.5B-LoRA

Updated about 7 hours ago

updated a model about 15 hours ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-1.5B-checkpoints

Updated about 7 hours ago

published a model about 15 hours ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-1.5B-checkpoints

Updated about 7 hours ago

updated a model 2 days ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-7B-LoRA

Updated 1 day ago • 1

published a model 2 days ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-7B-LoRA

Updated 1 day ago • 1

updated a model 2 days ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-7B-checkpoints

Updated 1 day ago

published a model 3 days ago

zcheng256/OPSD-SDPO-v22-Qwen2.5-7B-checkpoints

Updated 1 day ago

authored a paper 13 days ago

Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL

Paper • 2610.00574 • Published 15 days ago • 65

upvoted a paper 13 days ago

Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL

Paper • 2610.00574 • Published 15 days ago • 65

updated a dataset 13 days ago

zcheng256/searchforge-research-artifacts

Updated 12 days ago • 1.38k

published a dataset 21 days ago

zcheng256/searchforge-research-artifacts

Updated 12 days ago • 1.38k

updated a model 27 days ago

zcheng256/pure-opsd-r4-qwen3-1p7b-seed42-public

Text Generation • Updated 27 days ago

published a model 28 days ago

zcheng256/pure-opsd-r4-qwen3-1p7b-seed42-public

Text Generation • Updated 27 days ago

published 3 models about 1 month ago

zcheng256/rdgdpo-symmetric-math-7b-v07-seed0

Updated about 1 month ago

zcheng256/rdgdpo-symmetric-math-qwen3-4b-v07-seed0

Updated about 1 month ago

zcheng256/rdgdpo-symmetric-math-1.5b-v07-seed0

Updated about 1 month ago

updated a dataset about 1 month ago

zcheng256/opsd-instruction-scale-omni-full-v1-artifacts-public

Updated about 1 month ago • 388

published 2 models about 1 month ago

zcheng256/dvao-math-7b-v07-seed0-frozen-v2-250

Updated Sep 8

zcheng256/gd2po_hard-math-7b-v07-seed0-smoke-250-20260908

Updated Sep 8