Schedule
Schedule 12/3
https://neurips.cc/virtual/2022/workshop/49978
All times are with respect to the Central timezone. Please find links to the papers and SlidesLive videos at the above link.
Schedule | ||
---|---|---|
9:30 a.m. - 9.45 a.m. | Opening Remarks | Jessica Huynh |
9:45 a.m. - 10:15 a.m. | Invited Keynote by Jason Weston (Keynote) | Jason Weston |
10:15 a.m. - 10:25 a.m. | Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets (Oral) | Philippe Laban, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong |
10:25 a.m. - 10:35 a.m. | Are GAN Biased? Evaluating GAN-Generated Facial Images via Crowdsourcing (Oral) | Hangzhi Guo, Lizhen Zhu, Ting-Hao Huang |
10:35 a.m. - 10:45 a.m. | Towards Credible Human Evaluation of Open-Domain Dialog Systems Using Interactive Setup (Oral) | Sijia Liu, Patrick Lange, Behnam Hedayatnia, Alexandros Papangelis, Di Jin, Andrew Wirth, Yang Liu, Dilek Hakkani-Tur |
10:45 a.m. - 11:30 p.m. | Panel on Technical Challenges Associated with Reliable Human Evaluations of Generative Models (Discussion Panel) | Long Ouyang, Tongshuang Wu, Zachary Lipton |
11:30 p.m. - 1:00 p.m. | Lunch Break (Break) | |
1:00 p.m. - 1:50 p.m. | Discussion on Policy Challenges Associated with Generative Models (Discussion Panel) | Irene Solaiman, Russell Wald, Yonadav Shavit |
1:50 p.m. - 2:00 p.m. | Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark | Vitali Petsiuk, Alexander E. Siemenn, Saisamrit Surbehera, Zad Chin, Keith Tyser, Gregory Hunter, Arvind Raghavan, Yann Hicke, Bryan Plummer, Ori Kerret, Tonio Buonassisi, Kate Saenko, Armando Solar-Lezama, Iddo Drori |
2:00 p.m. - 2:10 p.m. | Can There be Art Without an Artist? (Oral) | Avijit Ghosh, Genoveva Fossas |
2:10 p.m. - 2:20 p.m. | Best Prompts for Text-to-Image Models and How to Find Them (Oral) | Nikita Pavlichenko, Fedor Zhdanov, Dmitry Ustalov |
2:20 p.m. - 2:30 p.m. | Evaluation of Synthetic Datasets for Conversational Recommender Systems (Oral) | Harsh Lara, Manoj Tiwari |
2:30 p.m. - 2:45 p.m. | Coffee Break (Break) | |
2:45 p.m. - 3:35 p.m. | Panel and QnA with Science Funders Interested in Reliable Human Evaluation of Generative Models (Panel) | Brittany Smith, Eric Sears, Yonadav Shavit |
3:35 p.m. - 3:45 p.m. | Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models (Oral) | Vikas Raunak, Matt Post, Arul Menezes |
3:45 p.m. - 3:55 p.m. | Sensemaking Interfaces for Human Evaluation of Language Model Outputs (Oral) | Katy Gero, Jonathan Kummerfeld, Elena Glassman |
3:55 p.m. - 4:05 p.m. | The Reasonable Effectiveness of Diverse Evaluation Data | Lora Aroyo, Mark Diaz, Christopher M. Homan, Vinodkumar Prabhakaran, Alex Taylor, Ding Wang |
4:05 p.m. - 4:15 p.m. | Closing Remarks | Jennifer Hsia |