Foundation models for agents, trustworthy LLMs/VLMs, deep RL
Optimization, acceleration, and efficient foundation-model training
Reinforcement learning and LLM post-training
Efficient algorithms and theory for modern ML systems
VLM agents and reinforcement learning for multi-step environments
Reinforcement learning, LLMs, autonomous agents, and reasoning
Deep learning, NLP, and LLM optimization
Diffusion and generative-model theory
Machine learning, optimization, and practical algorithms for LLMs
Formal reasoning and Lean for language models
Reliable generative models, continual learning, and agents
ML algorithms for decision making, embodied AI, and robotics
Generative models, LLM post-training, and multimodality