Registration and Check-in are located in the lobby of the convention center near the Radisson entrance.
Dialogue Research in the Era of LLMs
Recent large language models (LLMs) have enabled significant advancements for open-domain dialogue systems due to their ability to generate coherent natural language responses to any user request. Their ability to memorize and perform compositional reasoning has enabled accurate execution of dialogue related tasks, such as language understanding and response generation. However, these models suffer from limitations, such as, hallucination, undesired capturing of biases, difficulty in generalization to specific policies, and lack of interpretability.. To tackle these issues, the natural language processing community proposed methods, such as, injecting knowledge into language models during training or inference, retrieving related knowledge using multi-step inference and API/tools, and so on. In this talk, I plan to provide an overview of our and other work that aim to address these challenges.
Town Hall: LLMs in the ICLR Writing Process?
Topic: How much of using LLM should be allowed in academic paper writing? Pros and Cons?
Open discussion led by Sasha Rush (ICLR board) and ICLR 2023 Organizing committee.
Learned optimizers: why they're the future, why they’re hard, and what they can do now
The success of deep learning has hinged on learned functions dramatically outperforming hand-designed functions for many tasks. However, we still train models using hand designed optimizers acting on hand designed loss functions. I will argue that these hand designed components are typically mismatched to the desired behavior, and that we can expect meta-learned optimizers to perform much better. I will discuss the challenges and pathologies that make meta-training learned optimizers difficult. These include: chaotic and high variance meta-loss landscapes; extreme computational costs for meta-training; lack of comprehensive meta-training datasets; challenges designing learned optimizers with the right inductive biases; challenges interpreting the method of action of learned optimizers. I will share solutions to some of these challenges. I will show experimental results where learned optimizers outperform hand-designed optimizers in many contexts, and I will discuss novel capabilities that are enabled by meta-training learned optimizers.
