NeurIPS 2024 Workshop on Adaptive Foundation Models
Call for Papers
Important Dates and Links
Call for Papers
We are sourcing short, 4-5 page papers focusing on discrete abstractions such as objects, concepts, and events and the causal structure that relates them. Specific topics of interest include:
Continual Weight Updates
Techniques and challenges in updating model weights continually to adapt to new information without forgetting previously learned knowledge.
Efficient Fine-Tuning
Strategies to fine-tune models in a resource-efficient manner, enabling broader application without compromising performance.
Token/Prompt Tuning
Exploration of lightweight methods to adapt large models to specific tasks or domains through token or prompt modifications.
In-Context Learning/Few-Shot Learning
Mechanisms for models to learn from context within a limited interaction, and learn new concepts or tasks with very few examples.
Personalized Adaptation
Techniques for customizing models to individual user preferences, tasks, or domains, ensuring more relevant and effective interactions.
Retrieval-Augmented Generation
Integration of external knowledge sources to enhance the generation capabilities of models, facilitating more informed and contextually relevant outputs.
Multimodal Learning
Techniques for leveraging data from multiple modalities (e.g., text, images, robot interactions) into a unified framework, yielding rich interactivity.
Submission Policy
- We encourage 4 page submissions but are enforcing a hard maximum of 5, plus any number of pages for references and supplementary material. We reserve the right to desk reject papers that strongly violate this format (e.g. more than 5 pages main content before references)
- Submissions should be fully anonymized for double-blind review.
- Papers should use the NeurIPS style file.
- Dual submission policy: Submissions cannot have appeared at previous conferences or at NeurIPS 2024.
- Accepted submissions will appear on the workshop website (non-archival).