SD
Sombit Dey
cs.CVcs.ROcs.AI
On Valency
published · living versionsW_zx58p8qp·v1 · currentpublished
W_zkkfffzm·v1published
Preprints & journals
7 papers in the corpus · 2023–2026P-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models2610.28018v1 · Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey et al.2026 · 0 citationsarXivon Valency
Task-Adaptive Grounded 3D-Programmers Using 2D VLMs2610.02021v1 · Arman Raayatsanati, Sombit Dey, Anna-Maria Halacheva et al.2026 · 0 citationsarXiv
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models2603.10126v2 · Yutong Hu, Jan-Nico Zaech, Nikolay Nikolov et al.2026 · 0 citationsarXiv
From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding2507.17585v1 · Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey et al.2025 · 0 citationsarXiv
Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding2411.03405v1 · Sombit Dey, Ozan Unal, Christos Sakaridis et al.2024 · 0 citationsarXiv
ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models2409.15250v3 · Sombit Dey, Jan-Nico Zaech, Nikolay Nikolov et al.2024 · 7 citationsarXiv
Learning whom to trust in navigation: dynamically switching between classical and neural planning2307.16710v1 · Sombit Dey, Assem Sadek, Gianluca Monaci et al.2023 · 3 citationsarXiv
Career total: 10 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.