2 papers
cs.AI2026
Active Inference as Context Acquisition for AI Agents
Sanchayan Dutta, Sai Niranjan Ramachandran, Suvrit Sra
Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a def…
cs.LG2025
Toward generalizable learning of all (linear) first-order methods via memory augmented Transformers
Sanchayan Dutta, Suvrit Sra
We show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced metho…