Sambit Sahu

Principal Researcher, CapitalOne

2 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

#3519 · Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Sambit Sahu, Tom Goldstein, Supriyo Chakraborty

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

#1912 · Amartya Chakraborty, Paresh Dashore, Nadia Bathaee, Anmol Jain, Anirban Das, Shi-Xiong Zhang, Sambit Sahu, Milind Naphade, Genta Indra Winata

We introduce T1, a tool-augmented, multi-domain, multi-turn conversational dataset specifically designed to capture and manage inter-tool dependencies across diverse domains.