Berkeley Artificial Intelligence Research

(auto updated daily)

• TinyAgent: Function Calling at the Edge
  May 29, 2024
  The ability of LLMs to execute commands through plain language (e.g. English) has enabled agentic systems that can complete a user query by orchestrating the right set of tools (e.g. ToolFormer, Gorilla). This, along with the recent multi-modal efforts such as the GPT-4o or Gemini-1.5 model, has expanded the realm of possibilities with AI agents. […]

• TinyAgent: Function Calling at the Edge
• Modeling Extremely Large Images with xT
• 2024 BAIR Graduate Directory
• The Shift from Models to Compound AI Systems
• Ghostbuster: Detecting Text Ghostwritten by Large Language Models
• Asymmetric Certified Robustness via Feature-Convex Neural Networks
• Goal Representations for Instruction Following
• Rethinking the Role of PPO in RLHF
• Training Diffusion Models with Reinforcement Learning
• On the Stepwise Nature of Self-Supervised Learning