Schedule


                 
AM                      
8:40-9:00 Opening Remarks
9:00-9:30 Invited Talk 1 - Tatsunori Hashimoto
9:30-10:00 Invited Talk 2 - Nazneen Rajani
10:00-10:15 Break
10:15-10:45 Invited Talk 3 – Fei Xia
10:45-11:30 Panel 1: Key Techniques, Insights, and Challenges in Building Instruction-following Models
  Panelists: Alex Tamkin, Albert Webson, Fei Xia, Prithviraj (Raj) Ammanabrolu, Hyung Won Chung
PM  
13:00-14:00 Poster Session
14:00-14:30 Invited Talk 4 - Sara Hooker
14:30-15:00 Invited Talk 5 - Alex Tamkin
15:00-15:15 Break
15:15-16:00 Panel 2: Open and Collaborative Strategies for the Large Language Model Adaptation
  Panelists: Nazneen Rajani, Colin Raffel, Hao Zhang, Tatsunori Hashimoto
16:00-17:20 Oral Presentations (10 min each)
  1. Understanding Hidden Context in Preference Learning: Consequences for RLHF
  2. Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
  3. Understanding the Effects of RLHF on LLM Generalisation and Diversity
  4. Learning Interactive Real-World Simulators
  5. Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks
  6. Self-RAG: Self-reflective Retrieval Augmented Generation
  7. Delve into PPO: Implementation Matters for Stable RLHF
  8. FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
17:20-17:30 Closing Remarks