current research (independent researcher) Inference-time preference elicitation in multi-agent LLMs Eliciting preferences at inference time in multi-agent LLM settings. Details coming soon. Improving LLMs through multi-agent fine-tuning Using multi-agent fine-tuning to improve large language models. Details coming soon. masters @ Penn State Fine-tuning LLMs with RLHF Fine-tuning large language models using reinforcement learning with human feedback. Surprisingly popular voting Recovering the ground truth from crowds of experts and non-experts. NeurIPS 2024, WWW 2025 and KDD 2026. Breast cancer detection from mammograms CNN and attention-based models with image metadata integration. undergraduate @ NIT Rourkela Human gait as a cognitive state predictor Undergraduate thesis linking gait patterns to cognitive states. Multi-Kinect camera calibration Pairwise and octagonal calibration methods for multiple Kinect v2 sensors. CVIP 2021. Hand gesture password recognition A dynamic hand gesture-based password system. ICCIS 2019. Face detection and tracking Real-time face tracking with Viola-Jones detection and servo control.