arxiv:2606.29957
Zhuokai Zhao
zhuokai
AI & ML interests
Data-Efficient Learning, LLM Reasoning and Safety, Active Learning, Recommender System
Recent Activity
authored a paper about 22 hours ago
SWE-Together: Evaluating Coding Agents in Interactive User Sessions upvoted a paper 4 months ago
OmniOPD: Logit-Free On-Policy Distillation via Speculative VerificationOrganizations
models 8
zhuokai/dapo_baseline_without_dynamic_sampling_temperature_1.2_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/dapo_baseline_without_dynamic_sampling_temperature_1.0_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/dapo_baseline_without_dynamic_sampling_temperature_0.6_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/as_negexp_explore_1.2_stable_0.1_decay_freq_25_warmup_period_10_negexp_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/gpg_baseline_temperature_1.0_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/initial_grpo_baseline_temperature_0.6_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/initial_grpo_baseline_temperature_1.0_Qwen2.5-Math-1.5B_zzk
Updated
zhuokai/initial_grpo_baseline_temperature_1.2_Qwen2.5-Math-1.5B_zzk
Updated
datasets 0
None public yet