Sarath Chandar

AI agents must adapt to work effectively with new partners in various environments.

A new method enhances memory for better decision-making in RL agents.

Investigating how tools assist large language models in maintaining knowledge.

New algorithm enhances learning in real-world tasks without resets.

Understanding AI decision-making is crucial for trust and ethical use.

A new model that simplifies drug discovery by generating molecules efficiently.

Analyzing the factors affecting alignment in large language models.

This article examines how quantization can improve Transformer language model training efficiency.

Learn how smaller models can enhance the efficiency of large language models.

Researchers develop MergeAlign to make AI safer without losing expertise.

Examining how language models handle misleading information and their ability to adapt.