firstbacksecondback
18 Results
|
Workshop
|
Sat 1:45 |
AI Safety Institute |
|
|
Workshop
|
Sat 6:00 |
AISI: AI Safety Institute |
|
|
Workshop
|
Sat 0:45 |
Invited talk: UK Government AI Safety Institute |
|
| Thu 3:45 |
AI Safety Cesar Ilharco · Johannes Gasteiger · Bryan Perozzi |
||
|
Affinity Workshop
|
Tue 1:45 |
Fairness in AI: two philosophies or just one? MaryBeth Defrance |
|
|
Workshop
|
What's in Your "Safe" Data?: Identifying Benign Data that Breaks Safety Luxi He · Mengzhou Xia · Peter Henderson |
||
|
Poster
|
Wed 1:45 |
Towards Poisoning Fair Representations Tianci Liu · Haoyu Wang · Feijie Wu · Hengtong Zhang · Pan Li · Lu Su · Jing Gao |
|
|
Poster
|
Thu 1:45 |
Finetuning Text-to-Image Diffusion Models for Fairness Xudong Shen · Chao Du · Tianyu Pang · Min Lin · Yongkang Wong · Mohan Kankanhalli |
|
|
Workshop
|
Rethinking harmless refusals when fine-tuning foundation models Florin Pop · Judd Rosenblatt · Diogo de Lucena · Michael Vaiana |
||
|
Poster
|
Wed 1:45 |
Post-hoc bias scoring is optimal for fair classification Wenlong Chen · Yegor Klochkov · Yang Liu |
|
|
Workshop
|
What Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity from Incidental Causes Victor Lecomte · Kushal Thaman · Rylan Schaeffer · Naomi Bashkansky · Trevor Chow · Sanmi Koyejo |
||
|
Poster
|
Wed 1:45 |
Fair Classifiers that Abstain without Harm Tongxin Yin · Jean-Francois Ton · Ruocheng Guo · Yuanshun Yao · Mingyan Liu · Yang Liu |