Hao Jiang
Lutalica
AI & ML interests
Multimodal LLMs, LLM Reasoning, Reinforcement Learning, Efficient Inference
Recent Activity
authored a paper about 12 hours ago
D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use authored a paper about 12 hours ago
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization authored a paper about 12 hours ago
Pyramid Texture FilteringOrganizations
