Payal Fofadiya

Forget about bloated memory: structured forgetting boosts long-horizon agent performance by selectively pruning irrelevant information, achieving better F1 scores and reducing false memories.

Turn 2D orthographic views into 3D models automatically using corner detection and geometric reconstruction.

Dialogue agents can now remember what you told them six turns ago with 57% accuracy, thanks to a new memory architecture that selectively forgets less important details.

LLMs can maintain conversational stability and improve retrieval accuracy in long-running interactions by adaptively compressing context, leading to reduced token usage and faster inference.