22 citations · 61 across the 30 of their papers we have counts for
31 papers
GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
Arunabh Srivastava, Mohammad A., Khojastepour +2
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality na…
DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagery
Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradas +1
Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly, and often pose safety risks.…
Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery
Md Adnan Arefeen, Biplob Debnath, Ravi K. Rajendran +2
In satellite applications, user queries often take the form of open-ended natural language, extending beyond a fixed set of predefined categories. This open-vocabulary nature poses…
RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
Arunabh Srivastava, Mohammad A., Khojastepour +2
Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan exe…
Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation
Sarosij Bose, Ravi K. Rajendran, Biplob Debnath +3
Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical profess…
TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs
Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar
Traffic cameras are essential in urban areas, playing a crucial role in intelligent transportation systems. Multiple cameras at intersections enhance law enforcement capabilities,…
StreamingRAG: Real-time Contextual Retrieval and Generation Framework
Murugan Sankaradas, Ravi K. Rajendran, Srimat T. Chakradhar
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. H…
Re-ranking the Context for Multimodal Retrieval Augmented Generation
Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar +1
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and re…
RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar +1
Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particul…
iRAG: Advancing RAG for Videos with an Incremental Approach
Md Adnan Arefeen, Biplob Debnath, Md Yusuf Sarwar Uddin +1
Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG…
Deep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming
Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar +1
Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluc…
Deep Learning-Based Real-Time Rate Control for Live Streaming on Wireless Networks
Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar +1
Providing wireless users with high-quality video content has become increasingly important. However, ensuring consistent video quality poses challenges due to variable encoded bitr…
LeanContext: Cost-Efficient Domain-Specific Question Answering Using LLMs
Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar
Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, wide…
Differentiable JPEG: The Devil is in the Details
Christoph Reich, Biplob Debnath, Deep Patel +1
JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several dif…
Semantic Multi-Resolution Communications
Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar +1
Deep learning based joint source-channel coding (JSCC) has demonstrated significant advancements in data reconstruction compared to separate source-channel coding (SSCC). This supe…
Deep Video Codec Control for Vision Models
Christoph Reich, Biplob Debnath, Deep Patel +3
Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network ban…
5GLoR: 5G LAN Orchestration for enterprise IoT applications
Sandesh Dhawaskar Sathyanarayana, Murugan Sankaradas, Srimat Chakradhar
5G-LAN is an enterprise local area network (LAN) that leverages 5G technology for wireless connectivity instead of WiFi. 5G technology is unique: it uses network slicing to disting…
Elixir: A system to enhance data quality for multiple analytics on a video stream
Sibendu Paul, Kunal Rao, Giuseppe Coviello +4
IoT sensors, especially video cameras, are ubiquitously deployed around the world to perform a variety of computer vision tasks in several verticals including retail, healthcare, s…
APT: Adaptive Perceptual quality based camera Tuning using reinforcement learning
Sibendu Paul, Kunal Rao, Giuseppe Coviello +4
Cameras are increasingly being deployed in cities, enterprises and roads world-wide to enable many applications in public safety, intelligent transportation, retail, healthcare and…
Why is the video analytics accuracy fluctuating, and what can we do about it?
Sibendu Paul, Kunal Rao, Giuseppe Coviello +4
It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on v…
ROMA: Resource Orchestration for Microservices-based 5G Applications
Anousheh Gholami, Kunal Rao, Wang-Pin Hsiung +3
With the growth of 5G, Internet of Things (IoT), edge computing and cloud computing technologies, the infrastructure (compute and network) available to emerging applications (AR/VR…
Edge-based fever screening system over private 5G
Murugan Sankaradas, Kunal Rao, Ravi Rajendran +2
Edge computing and 5G have made it possible to perform analytics closer to the source of data and achieve super-low latency response times, which is not possible with centralized c…
SmartSlice: Dynamic, self-optimization of applications QoS requests to 5G networks
Kunal Rao, Murugan Sankaradas, Vivek Aswal +1
Applications can tailor a network slice by specifying a variety of QoS attributes related to application-specific performance, function or operation. However, some QoS attributes l…
DataX: A system for Data eXchange and transformation of streams
Giuseppe Coviello, Kunal Rao, Murugan Sankaradas +1
The exponential growth in smart sensors and rapid progress in 5G networks is creating a world awash with data streams. However, a key barrier to building performant multi-sensor, d…