xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_75
3B • Updated • 6
wang PRO
xinpeng
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Self-Distillation with Verbal Regularization upvoted a paper 11 days ago
OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation submitted a paper 11 days ago
OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy DistillationOrganizations
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_35
3B • Updated • 6
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_60
3B • Updated • 8
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_10
3B • Updated • 5
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_50
3B • Updated • 6
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-rm-loophole-global_step_45
3B • Updated • 9
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_90
Text Generation • 3B • Updated • 18
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_85
3B • Updated • 10
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_80
Text Generation • 3B • Updated • 19
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_75
Text Generation • 3B • Updated • 16
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_70
Text Generation • 3B • Updated • 18
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_65
Text Generation • 3B • Updated • 21
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_60
Text Generation • 3B • Updated • 16
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_50
Text Generation • 3B • Updated • 18
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_55
Text Generation • 3B • Updated • 22
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_45
Text Generation • 3B • Updated • 14
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_40
Text Generation • 3B • Updated • 19
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_35
Text Generation • 3B • Updated • 13
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_30
Text Generation • 3B • Updated • 14
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_25
Text Generation • 3B • Updated • 24
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_20
Text Generation • 3B • Updated • 22
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_5
Text Generation • 3B • Updated • 19
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_10
Text Generation • 3B • Updated • 17
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no-global_step_15
Text Generation • 3B • Updated • 21
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_25
3B • Updated • 7
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_20
3B • Updated • 7
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_15
3B • Updated • 7
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_30
3B • Updated • 7
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_10
3B • Updated • 11
xinpeng/kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo-global_step_5
3B • Updated • 7