Call for Papers

We invite submissions on any aspect of trustworthy and reliable ML, especially for large-scale models. Topics include but are not limited to:

• Novel methods for building more trustworthy large-scale machine learning models that prevent or alleviate negative societal impacts of existing ML methods
• New applications and settings where the robustness and trustworthiness of machine learning play an important role and how well existing techniques work under these settings
• Machine learning models with verifiable guarantees (such as robustness, fairness, and privacy guarantees) to build trustworthiness
• Privacy-preserving machine learning approaches for large-scale machine learning models
• Theoretical understanding of trustworthy machine learning
• Explainable and interpretable methods for large-scale AI
• Pre-training techniques to build more robust and trustworthy large-scale machine learning models
• Efficient fine-tuning methods to alleviate the trustworthiness gap for large-scale pre-trained models
• Machine unlearning to mitigate the privacy, toxicity, and bias issues within large-scale AI models
• Robust decision-making under uncertainty
• Futuristic concerns about trustworthy machine learning for foundation models
• Game-theoretic analysis for socially responsible machine learning systems
• Case studies and field research of the societal impacts of applying machine learning in mission-critical and human-centric tasks

We only consider submissions that haven’t been published in any peer-reviewed venue, including ICLR 2023 conference. The workshop is non-archival and will not have any official proceedings. Based on the PC’s recommendation, the accepted papers will be allocated either a contributed talk or a poster presentation.

We offer a Best Paper Award ($1,000), a Best Paper Honorable Mention Award ($500), and several travel grants (complimentary ICLR conference registrations).