3 papers
cs.RO2026
Search, Ground, Plan: Functional Sufficiency for Task and Motion Planning under Incomplete Scene Knowledge
Narendhiran Vijayakumar, Nav Singhal, Girish Varma +1
Foundation models (FMs) have expanded task and motion planning (TAMP) to manipulation problems specified through language and visual observations. However, incomplete scene knowled…
cs.RO2026
Deciding If, When, and Where to Replan for Robust Manipulation
Puru Ojha, Narendhiran Vijayakumar, Nav Singhal +2
Foundation-model (FM) based task and motion planning (TAMP) methods typically assume that the full scene is known before planning. In long-horizon manipulation, however, relevant o…
cs.LG2026
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
Daniel Goldstein, Navneel Singhal, Eugene Cheah
Recall presents a difficult choice: transformers have a linearly growing memory that slows each successive token, while linear RNNs typically have fixed costs but limited recall. W…