3 papers
cs.AI2026
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
Jayant Parashar, Suchendra M. Bhandarkar
Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accumulated in one growing promp…
cs.CV2026
Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction
Devjyoti Chakraborty, Zaki Sukma, Rakandhiya D. Rachmanto +6
Neural Radiance Fields (NeRF) have emerged as a powerful approach for photorealistic 3D reconstruction from multi-view images. However, deploying NeRF for satellite imagery remains…
cs.CV2025
-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer
Kriti Ghosh, Devjyoti Chakraborty, Lakshmish Ramaswamy +4
Neural Radiance Fields (NeRFs) have demonstrated remarkable capabilities in 3D reconstruction and novel view synthesis. However, most existing NeRF frameworks require complete retr…