Events

Cindy Wang (Google DeepMind) “Building Data-Efficient and Reliable Applications with Large Language Models”

February 29, 2024
When: March 8, 2024 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, it is still very challenging to build highly-reliable applications with LLMs that support specialized use cases. LLMs trained on web data often[…]

Read More

Rachel Wicks (JHU) “To Sentences and Beyond: Paving the Way for Context-Aware Machine Translation”

February 26, 2024
When: March 4, 2024 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Most machine translation systems operate on the sentence-level while humans write and translate within a given context. Operating on individual sentences forces error-prone sentence segmentation into the machine translation pipeline. This limits the upper-bound[…]

Read More

Keith Harrigian (JHU) “Fighting Bias From Bias: Robust Natural Language Processing Techniques to Promote Health Equity”

February 26, 2024
When: February 26, 2024 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract As artificial intelligence (AI) continues to rapidly expand into existing healthcare infrastructure – e.g., clinical decision support, administrative tasks, and public health surveillance – it is perhaps more important than ever to reflect on[…]

Read More

Ioana Ciuca (Australian National University)”A Universe To Be Decided: Towards Specialized Foundation Models for Advancing Astronomy”

February 20, 2024
When: February 23, 2024 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract I discuss the application of Foundation Models in Astronomy through the collaborative efforts of the UniverseTBD consortium with a mission to democratize Science for everyone. One of our key objectives is to overcome the[…]

Read More

Steven Tan “Streaming Sequence Transduction through Dynamic Compression”

February 20, 2024
When: February 19, 2024 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x)[…]

Read More

Center for Language and Speech Processing