Bhuvan Sachdeva

I'm a Member of Technical Staff at Stellon Labs, where I work on text-to-speech (TTS) and automatic speech recognition (ASR) models. I joined in July 2026.

Previously, I was a research fellow at Sankara Eye Hospital and Microsoft Research India, where I worked with Dr. Mohit Jain, Dr. Vineeth N B, and Prof. Thomas Schultz.

My research spans speech, vision-language models, and healthcare AI. My previous work includes task-transfer dynamics in vision-language models, surgical scene understanding in cataract surgery, and expert-in-the-loop LLM chatbots for patients and community health workers.

I received my B.Tech. in Computer Science from Delhi Technological University (DTU) in 2023. During my undergrad, I interned at Prime Video, Amazon and Kroop AI.

Bhuvan Sachdeva

News

Selected Papers (full list)

BAGEL-RL
Embodied Spatial Reasoning @ NeurIPS 2026
BAGEL-RL: Low-Rank Reinforcement Learning for Interleaved Visual Reasoning

Bhuvan Sachdeva, Vineeth N. Balasubramanian

We introduce a parameter-efficient adaptation of BAGEL using Group Relative Policy Optimization (GRPO) with Low-Rank Adaptation (LoRA) for interleaved visual reasoning. BAGEL-RL improves average benchmark performance from 62.49% to 70.36% while updating only 2.6% of the model parameters.

Task Transfer
CVPR 2026 (Oral)
Understanding Task Transfer in Vision-Language Models

Bhuvan Sachdeva*, Karan Uppal*, Abhinav Java*, Vineeth N. Balasubramanian

We investigate how finetuning on one task affects zero-shot performance on others across the Qwen-2.5-VL model family. We introduce the Perfection Gap Factor (PGF) to characterize task-to-task transfer and leverage task interactions to identify effective proxy datasets.

Swift Sampling
NeurIPS 2026
Swift Sampling: Selecting Temporal Surprises via Taylor Series

Dahye Kim, Bhuvan Sachdeva*, Karan Uppal*, Naman Gupta*, Vineeth N. Balasubramanian, Deepti Ghadiyaram

A training-free, lightweight frame selection algorithm for long-video understanding. We model a video as a differentiable trajectory in visual latent space and use a Taylor expansion to predict future features; frames with large residuals ("temporal surprises") are selected as keyframes. Adds only 0.02× overhead while improving VQA accuracy by up to +12.5 points.

ToolSeg
MICCAI 2025
Phase-Informed Tool Segmentation for Manual Small-Incision Cataract Surgery

Bhuvan Sachdeva*, Naren Akash*, Tajamul Ashraf, Simon Müller, Thomas Schultz, Maximilian W.M. Wintergerst, Niharika Singri Prasad, Kaushik Murali, Mohit Jain

We present the first comprehensive dataset for MSICS cataract surgery tool segmentation and introduce ToolSeg, a phase-informed segmentation method that leverages surgical phases to enhance tool segmentation accuracy.

CataractBot
UbiComp 2025
CataractBot: an LLM-powered expert-in-the-loop chatbot for cataract patients

Pragnya Ramjee*, Bhuvan Sachdeva*, Satvik Golechha, Shreyas Kulkarni, Geeta Fulari, Kaushik Murali, Mohit Jain

We developed CataractBot, an LLM-powered chatbot answering cataract surgery questions via a curated knowledge base with expert-verified responses, supporting multimodal and multilingual inputs.