Yunfan Liu
yf-liu
AI & ML interests
None yet
Recent Activity
updated a collection 17 days ago
Think-with-Image updated a collection 21 days ago
Think-with-Image updated a collection 21 days ago
OPDOrganizations
None yet
Training_Data_Synthesis
OPD
-
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Paper • 2607.29209 • Published • 34 -
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 101 -
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Paper • 2608.05131 • Published • 14 -
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 218
dLLM_Continuous
Think-with-Image
-
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Paper • 2608.01827 • Published • 18 -
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Paper • 2608.08021 • Published • 16 -
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
Paper • 2608.06270 • Published • 8
AI4AI
Agent
Training_Data_Synthesis
dLLM_MoE
OPD
-
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Paper • 2607.29209 • Published • 34 -
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 101 -
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Paper • 2608.05131 • Published • 14 -
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 218
Daily_Intake
dLLM_Continuous
dLLM_AR2
Think-with-Image
-
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Paper • 2608.01827 • Published • 18 -
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Paper • 2608.08021 • Published • 16 -
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
Paper • 2608.06270 • Published • 8
Agent_Skill