Aleksandar Petrov

Venues

Frequent coauthors

Papers

1. Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language ModelsBibTeX ⧉
   ICLR 2025 ·

   Francisco Eiras

   , Aleksandar Petrov,

   Philip Torr

   ,

   M. Pawan Kumar

   ,

   Adel Bibi
2. Language-Models-as-a-Service: Overview of a New Paradigm and its ChallengesBibTeX ⧉
   AAAI 2025 ·

   Emanuele La Malfa

   , Aleksandar Petrov,

   Simon Frieder

   ,

   Christoph Weinhuber

   ,

   Ryan Burnell

   ,

   Raza Nazar

   ,

   Anthony G. Cohn

   ,

   Nigel Shadbolt

   ,

   Michael J. Wooldridge
3. On the Coexistence and Ensembling of WatermarksBibTeX ⧉
   NeurIPS 2025 · Aleksandar Petrov,

   Shruti Agarwal

   ,

   Philip H. S. Torr

   ,

   Adel Bibi

   ,

   John P. Collomosse
4. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AIBibTeX ⧉
   ICML 2024 ·

   Francisco Eiras

   , Aleksandar Petrov,

   Bertie Vidgen

   ,

   Christian Schröder de Witt

   ,

   Fabio Pizzati

   ,

   Katherine Elkins

   ,

   Supratik Mukhopadhyay

   ,

   Adel Bibi

   ,

   Botos Csaba

   ,

   Fabro Steibel

   ,

   Fazl Barez

   ,

   Genevieve Smith

   ,

   Gianluca Guadagni

   ,

   Jon Chun

   ,

   Jordi Cabot

   ,

   Joseph Marvin Imperial

   ,

   Juan A. Nolazco-Flores

   ,

   Lori Landay

   ,

   Matthew Thomas Jackson

   ,

   Paul Röttger

   ,

   Philip H. S. Torr

   ,

   Trevor Darrell

   ,

   Yong Suk Lee

   ,

   Jakob N. Foerster
5. Prompting a Pretrained Transformer Can Be a Universal ApproximatorBibTeX ⧉
   ICML 2024 · Aleksandar Petrov,

   Philip Torr

   ,

   Adel Bibi
6. Universal In-Context Approximation By Prompting Fully Recurrent ModelsBibTeX ⧉
   NeurIPS 2024 · Aleksandar Petrov,

   Tom A. Lamb

   ,

   Alasdair Paren

   ,

   Philip Torr

   ,

   Adel Bibi
7. When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and LimitationsBibTeX ⧉
   ICLR 2024 · Aleksandar Petrov,

   Philip Torr

   ,

   Adel Bibi