Seminars
| Sun | Mon | Tue | Wed | Thu | Fri | Sat |
|---|---|---|---|---|---|---|
|
Propaganda is already influencing large language models: evidence from training data, audits, and real-world usage – Brandon Stewart (Princeton)
12:00 pm
Propaganda is already influencing large language models: evidence from training data, audits, and real-world usage – Brandon Stewart (Princeton)
@ Hackerman Hall B17
Oct 3 @ 12:00 pm β 1:15 pm
Abstract Millions of people around the world query (prompt) large language models for information. While several studies have compellingly documented the persuasive potential of these models, there is limited evidence of who or what influences[...]
|
||||||
|
Voice Conversion: Background and Challenges – Henry Li (JHU)
12:00 pm
Voice Conversion: Background and Challenges – Henry Li (JHU)
@ Hackerman Hall B17
Oct 6 @ 12:00 pm β 1:30 pm
Abstract Unstructured data is pervasive in our daily lives, appearing in forms such as meeting and interview transcripts, written notes, and social media posts. These data often contain valuable human knowledge and insights. To uncover[...]
|
LLMs in Science: The Good, The Bad and The Ugly – Nihar Shah (CMU)
12:00 pm
LLMs in Science: The Good, The Bad and The Ugly – Nihar Shah (CMU)
@ Hackerman Hall B17
Oct 10 @ 12:00 pm β 1:15 pm
Abstract As LLMs become increasingly integrated into academic workflows, their influence is both promising and precarious. In this talk, we will explore three facets of this evolving intersection. – The Good:Β LLMs executing aspects of peer[...]
|
|||||
|
Exploring Self-Play Beyond Competition: Language Model Learning in Negotiation Games – Austen Liao (JHU)
12:00 pm
Exploring Self-Play Beyond Competition: Language Model Learning in Negotiation Games – Austen Liao (JHU)
@ Hackerman Hall B17
Oct 13 @ 12:00 pm β 1:30 pm
Abstract Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However, most language tasks are partially or fully cooperative, so it is an[...]
Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents – Nikhil Sharma (JHU)
12:00 pm
Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents – Nikhil Sharma (JHU)
Oct 13 @ 12:00 pm β 1:30 pm
Abstract High-quality user feedback is essential for effective human-AI interaction. It bridges knowledge gaps, corrects drift, and shapes system behavior; both during the interaction and throughout model development. Β However, despite its importance, in-the-wild human-AI conversations[...]
|
||||||
|
How to Design Better Posters – Yu Lu Liu (JHU)
12:00 pm
How to Design Better Posters – Yu Lu Liu (JHU)
@ Hackerman Hall B17
Oct 20 @ 12:00 pm β 1:30 pm
Abstract Poster presentations are a key part of academic conferences, and sometimes, a poster session is the only opportunity we get at presenting our papers. It is thus very important to take full advantage of[...]
|
Modeling implicit othering in sociopolitical discourse – Julia Mendelsohn (UMD College Park)
12:00 pm
Modeling implicit othering in sociopolitical discourse – Julia Mendelsohn (UMD College Park)
@ Hackerman Hall B17
Oct 24 @ 12:00 pm β 1:30 pm
Abstract When discussing politics, people often use subtle linguistic strategies to influence how their audience thinks about issues, which can then impact public opinion and policy. For example, anti-immigration activists may frame immigration as a[...]
|
|||||
|
The Alignment Waltz: Jointly Training Agents to Collaborate for Safety – Jack Zhang (JHU)
12:00 pm
The Alignment Waltz: Jointly Training Agents to Collaborate for Safety – Jack Zhang (JHU)
@ Hackerman Hall B17
Oct 27 @ 12:00 pm β 1:30 pm
Abstract Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency[...]
|
Subscribe to filtered calendar
