3 papers
cs.CV2026
COMBAT: Conditional World Models for Behavioral Agent Training
Anmol Agarwal, Pranay Meshram, Sumer Singh +5
Recent advances in video generation have spurred the development of world models capable of simulating 3D-consistent environments and interactions with static objects. However, a s…
cs.RO2026
CLEAR: A Semantic-Geometric Terrain Abstraction for Large-Scale Unstructured Environments
Pranay Meshram, Charuvahan Adhivarahan, Ehsan Tarkesh Esfahani +3
Long-horizon navigation in unstructured environments demands terrain abstractions that scale to tens of square kilometers while preserving semantic and geometric structure. Grids s…
cs.CV2025
QAL: A Loss for Recall Precision Balance in 3D Reconstruction
Pranay Meshram, Yash Turkar, Kartikeya Singh +3
Volumetric learning underpins many 3D vision tasks such as completion, reconstruction, and mesh generation, yet training objectives still rely on Chamfer Distance (CD) or Earth Mov…