firstbacksecondback
26 Results
|
Workshop
|
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs Megh Thakkar · Yash More · Quentin Fournier · Matthew Riemer · Pin-Yu Chen · Amal Zouaq · Payel Das · Sarath Chandar |
||
|
Workshop
|
The Rate-Distortion-Perception Trade-Off with Algorithmic Realism Yassine Hamdi · Aaron Wagner · Deniz Gunduz |