Abhishek Sehgal

Structure and Diversity Aware Context Bubble Construction for Enterprise Retrieval Augmented Systems

Amir Khurshid, Abhishek Sehgal

Large language model (LLM) contexts are typically constructed using retrieval-augmented generation (RAG), which involves ranking and selecting the top-k passages. The approach causes fragmentation in information graphs in document structures, over-retrieval, and duplication of content alongside insufficient query context, including 2nd and …

Structure and Diversity Aware Context Bubble Construction for Enterprise Retrieval Augmented Systems

Amir Khurshid, Abhishek Sehgal

Large language model (LLM) contexts are typically constructed using retrieval-augmented generation (RAG), which involves ranking and selecting the top-k passages. The approach causes fragmentation in information graphs in document structures, over-retrieval, and duplication of content alongside insufficient query context, including 2nd and …

R&D Alpha: Investment Intensity and Long-Term Stock Returns

Abhishek Sehgal

us (code pays fourni par la source)

Did Fundamentals Justify the AI Repricing of Enterprise Software/ (SaaS Valuations)? Evidence from 2023-2026

Abhishek Sehgal

us (code pays fourni par la source)

DuraLoop: Reducing Rework, Cost, and Customer-Visible Errors in AI Coding Agents. A Production Case Study and Operational Framework for Reducing Rework in AI Coding-agent Fleets

Abhishek Sehgal, Chitrita Goswami

Harnessing the potential of emerging additive manufacturing technologies as a game-changer for chemical and biosensing innovations

Ashish Kalkal, Amit Kumar Yadav, Damini Verma, Abhishek Sehgal et autres

Over the past four decades, additive manufacturing (AM), particularly three-dimensional (3D) printing, has emerged as a transformative force in chemical and biosensing technologies, revolutionizing prototyping and production across laboratories and industries. Recent advancements in 3D printing techniques and materials have accelerated the …

in, gb (code pays fourni par la source)

A Low-Duty-Cycle and Congestion-Robust Design of Adaptive Wi-Fi 7 Multi-Link Operation Control Over User Side

Yirong Cheng, Abhishek Sehgal, Kyeong Jin Kim, Neha Dawar et autres

Wi-Fi 7 has been developed recently to support newapplications such as 4K videos and AR/VR, which demand higher network throughput and lower latency. One of its key features, Multi-link Operation (MLO), enables Wi-Fi 7 to utilize multiple carrier frequencies, enhancing throughput and …

us (code pays fourni par la source)

Enhancing Wi-Fi 7: Traffic Flow Intelligence and Multi-Link Operation for Optimal Efficiency

Neha Dawar, Khuong N. Nguyen, Abhishek Sehgal, Yuming Zhu et autres

As the proliferation of Wi-Fi-enabled devices continues to accelerate, there is a pressing need for efficient wireless connectivity solutions. To address this challenge, the introduction of Multi-Link Operation (MLO) inWi-Fi 7 (IEEE 802.11be) enables clients to establish connections with access points across …

us, kr (code pays fourni par la source)

End-to-end system for real-time bidirectional holographic communication

Indranil Sinharoy, Madhukar Budagavi, Esmaeil Faramarzi, Saifeng Ni et autres

Recent advancements in volumetric displays have opened doors to immersive, glass-free holographic experiences in our everyday environments. This paper introduces Holoportal, a real-time, low-latency system that captures, processes, and displays 3D video of two physically separated individuals as if they are conversing …

us (code pays fourni par la source)

Eyeball tracking in closed eyes from shadows

Indranil Sinharoy, Aditya Dave, Lianjun Li, Hao Chen et autres

The capacity to track eyeball movements beneath closed eyelids holds significant promise across commercial, security, and medical domains. Our work presents a simple, effective, non-invasive method for closed-eye eyeball motion detection using videos. This method relies on detecting the temporal variations in …

us, kr (code pays fourni par la source)

Data augmentation and synthesis of radar signatures for ML-based gesture recognition and activity detection from MoCap trajectories

Indranil Sinharoy, Aditya Dave, Gaurav Duggal, Vutha Va et autres

Optimal Preprocessing of WiFi CSI for Sensing Applications

V. V. Ratnam, Hao Chen, Hao-Hsuan Chang, Abhishek Sehgal et autres

Due to its ubiquitous and contact-free nature, the use of WiFi infrastructure for performing sensing tasks has tremendous potential. However, the channel state information (CSI) measured by a WiFi receiver suffers from errors in both its gain and phase, which can significantly …

us (code pays fourni par la source)