arxiv:2504.20771
HaitaoWu
Haitao999
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models upvoted a paper 1 day ago
Rethinking the Divergence Regularization in LLM RL upvoted a paper 1 day ago
Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur PriorOrganizations
None yet
models 45
Haitao999/ubp_exp
Updated
Haitao999/Llama-3.2-3B-Instruct-EMPO-numia_prompt_dpo1
Text Generation • 3B • Updated • 1
Haitao999/Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1
Text Generation • 3B • Updated • 1
Haitao999/Qwen3-0.6B-Instruct-EMPO-numia_prompt_dpo1
Updated
Haitao999/Qwen2.5-7B-GRPO-Natural-Reasoning-0428-continue
8B • Updated • 1
Haitao999/Qwen2.5-7B-GRPO-Natural-Reasoning-0428
Text Generation • 8B • Updated • 1
Haitao999/Qwen2.5-7B-Base-EMPO-natural_reasoning_all_level
Text Generation • 8B • Updated • 1
Haitao999/Qwen2.5-7B-Base-EMPO-WebInstruct-verified
8B • Updated • 1
Haitao999/Qwen2.5-7B-Instruct-EMPO-natural_reasoning_simple-0419
Text Generation • 8B • Updated • 2
Haitao999/Qwen2.5-7B-Instruct-EMPO-natural_reasoning_simple_from_base_general-verifier
Text Generation • 8B • Updated • 1