Srimat Chakradhar
Srimat Chakradhar has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Kunal Rao
NEC Laboratories America, Inc
9 shared publications - Murugan Sankaradas
NEC Laboratories America, Inc
8 shared publications - Giuseppe Coviello
NEC Laboratories America, Inc
6 shared publications - Mohammad A. Amir Khojastepour
NEC Laboratories America Princeton NJ
5 shared publications - Matin Mortaheb
Department of Electrical and Computer Engineering University of Maryland 20742 College Park MD
4 shared publications - Sennur Ulukus
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
4 shared publications
Latest Publications
- 27 August 2025
- Published by Springer Nature
- p. 279-291
Bifröst: Peer-to-Peer Load-Balancing for Function Execution in Agentic AI Systems
- 27 August 2025
- Published by Springer Nature
- p. 279-291
Bifröst: Peer-to-Peer Load-Balancing for Function Execution in Agentic AI Systems
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
XPF: Agentic AI System for Business Workflow Automation
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessXPF: Agentic AI System for Business Workflow Automation
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2469-2479
Roadside Multi-LiDAR Data Fusion for Enhanced Traffic Safety
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2469-2479
Open AccessRoadside Multi-LiDAR Data Fusion for Enhanced Traffic Safety
- Open Access
Re-ranking the Context for Multimodal Retrieval Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-$k$ entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.
Open AccessRe-ranking the Context for Multimodal Retrieval Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-$k$ entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.
- Open Access
RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g., documents, images) as raw context from the database, and (ii) retrieved images are processed into text-based context via vision-language models (VLMs) or directly used by multi-modal language models (MLLMs) like GPT-4o, which may hallucinate. To address this, we propose a novel framework to evaluate the reliability of multi-modal RAG using two performance measures: (i) the relevancy score (RS), assessing the relevance of retrieved entries to the query, and (ii) the correctness score (CS), evaluating the accuracy of the generated response. We train RS and CS models using a ChatGPT-derived database and human evaluator samples. Results show that both models achieve ~88% accuracy on test data. Additionally, we construct a 5000-sample human-annotated database evaluating the relevancy of retrieved pieces and the correctness of response statements. Our RS model aligns with human preferences 20% more often than CLIP in retrieval, and our CS model matches human preferences ~91% of the time. Finally, we assess various RAG systems' selection and generation performances using RS and CS.
Open AccessRAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g., documents, images) as raw context from the database, and (ii) retrieved images are processed into text-based context via vision-language models (VLMs) or directly used by multi-modal language models (MLLMs) like GPT-4o, which may hallucinate. To address this, we propose a novel framework to evaluate the reliability of multi-modal RAG using two performance measures: (i) the relevancy score (RS), assessing the relevance of retrieved entries to the query, and (ii) the correctness score (CS), evaluating the accuracy of the generated response. We train RS and CS models using a ChatGPT-derived database and human evaluator samples. Results show that both models achieve ~88% accuracy on test data. Additionally, we construct a 5000-sample human-annotated database evaluating the relevancy of retrieved pieces and the correctness of response statements. Our RS model aligns with human preferences 20% more often than CLIP in retrieval, and our CS model matches human preferences ~91% of the time. Finally, we assess various RAG systems' selection and generation performances using RS and CS.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4341-4348
iRAG: Advancing RAG for Videos with an Incremental Approach
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 for understanding of videos is appealing but there are two critical limitations. One-time, upfront conversion of all content in large corpus of videos into text descriptions entails high processing times. Also, not all information in the rich video data is typically captured in the text descriptions. Since user queries are not known apriori, developing a system for video to text conversion and interactive querying of video data is challenging. To address these limitations, we propose an incremental RAG system called iRAG, which augments RAG with a novel incremental workflow to enable interactive querying of a large corpus of videos. Unlike traditional RAG, iRAG quickly indexes large repositories of videos, and in the incremental workflow, it uses the index to opportunistically extract more details from select portions of the videos to retrieve context relevant to an interactive user query. Such an incremental workflow avoids long video to text conversion times, and overcomes information loss issues due to conversion of video to text, by doing on-demand query-specific extraction of details in video data. This ensures high quality of responses to interactive user queries that are often not known apriori. To the best of our knowledge, iRAG is the first system to augment RAG with an incremental workflow to support efficient interactive querying of a large corpus of videos. Experimental results on real-world datasets demonstrate 23x to 25x faster video to text ingestion, while ensuring that latency and quality of responses to interactive user queries is comparable to responses from a traditional RAG where all video data is converted to text upfront before any user querying.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4341-4348
Open AccessiRAG: Advancing RAG for Videos with an Incremental Approach
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 for understanding of videos is appealing but there are two critical limitations. One-time, upfront conversion of all content in large corpus of videos into text descriptions entails high processing times. Also, not all information in the rich video data is typically captured in the text descriptions. Since user queries are not known apriori, developing a system for video to text conversion and interactive querying of video data is challenging. To address these limitations, we propose an incremental RAG system called iRAG, which augments RAG with a novel incremental workflow to enable interactive querying of a large corpus of videos. Unlike traditional RAG, iRAG quickly indexes large repositories of videos, and in the incremental workflow, it uses the index to opportunistically extract more details from select portions of the videos to retrieve context relevant to an interactive user query. Such an incremental workflow avoids long video to text conversion times, and overcomes information loss issues due to conversion of video to text, by doing on-demand query-specific extraction of details in video data. This ensures high quality of responses to interactive user queries that are often not known apriori. To the best of our knowledge, iRAG is the first system to augment RAG with an incremental workflow to support efficient interactive querying of a large corpus of videos. Experimental results on real-world datasets demonstrate 23x to 25x faster video to text ingestion, while ensuring that latency and quality of responses to interactive user queries is comparable to responses from a traditional RAG where all video data is converted to text upfront before any user querying.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 7-12
ECO-LLM: LLM-based Edge Cloud Optimization
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too much time and effort, and is very painful. In this paper, we propose a novel technique using Generative Artificial Intelligence (GenAI) technology, wherein instructions can be provided in natural language and actual code to handle any customization is automatically generated, integrated and applied on-the-fly. Such capability is extremely powerful since it makes customization of application settings or solution techniques super easy. Specifically, we propose ECO-LLM (LLM-based Edge Cloud Optimization), which leverages Large Language Models (LLM) to dynamically adjust placement of application tasks across edge and cloud computing tiers, in response to changes in application workload, such that insights are delivered quickly with low cost of operation (systems problem). Our experiments with real-world video analytics applications i.e. face recognition, human attributes detection and license plate recognition show that ECO-LLM is able to automatically generate code on-the-fly and adapt placement of application tasks across edge and cloud computing tiers. We note that the trigger workload (to switch between edge and cloud) for ECO-LLM is exactly the same as the baseline (manual) and actual placement performed by ECO-LLM is only slightly different i.e. on average (across 2 days) only 1.45% difference in human attributes detection and face recognition, and 1.11% difference in license plate recognition. Although we tackle this specific systems problem in this paper, our proposed GenAI-based technique is applicable to solve other systems problems too.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 7-12
Open AccessECO-LLM: LLM-based Edge Cloud Optimization
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too much time and effort, and is very painful. In this paper, we propose a novel technique using Generative Artificial Intelligence (GenAI) technology, wherein instructions can be provided in natural language and actual code to handle any customization is automatically generated, integrated and applied on-the-fly. Such capability is extremely powerful since it makes customization of application settings or solution techniques super easy. Specifically, we propose ECO-LLM (LLM-based Edge Cloud Optimization), which leverages Large Language Models (LLM) to dynamically adjust placement of application tasks across edge and cloud computing tiers, in response to changes in application workload, such that insights are delivered quickly with low cost of operation (systems problem). Our experiments with real-world video analytics applications i.e. face recognition, human attributes detection and license plate recognition show that ECO-LLM is able to automatically generate code on-the-fly and adapt placement of application tasks across edge and cloud computing tiers. We note that the trigger workload (to switch between edge and cloud) for ECO-LLM is exactly the same as the baseline (manual) and actual placement performed by ECO-LLM is only slightly different i.e. on average (across 2 days) only 1.45% difference in human attributes detection and face recognition, and 1.11% difference in license plate recognition. Although we tackle this specific systems problem in this paper, our proposed GenAI-based technique is applicable to solve other systems problems too.
- Open Access
- 18 March 2024
- Published by Elsevier in Natural Language Processing Journal
- Vol. 7, 100065
LeanContext: Cost-efficient domain-specific question answering using LLMs
- 18 March 2024
- Published by Elsevier in Natural Language Processing Journal
- Vol. 7, 100065
Open AccessLeanContext: Cost-efficient domain-specific question answering using LLMs
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 68, 584-591
Scale Up while Scaling Out Microservices in Video Analytics Pipelines
Modern video analytics applications comprise multiple microservices chained together as pipelines and executed on container orchestration platforms like Kubernetes. Kubernetes automatically handles the scaling of these microservices for efficient application execution. There are two popular choices for scaling microservices in Kubernetes i.e. scaling Out using Horizontal Pod Autoscaler (HPA) and scaling Up using Vertical Pod Autoscaler (VPA). Both these have been studied independently, but there isn’t much prior work studying the joint scaling of these two. This paper investigates joint scaling, i.e., scaling up while scaling out (HPA) is in action. In particular, we focus on scaling up CPU resources allocated to the application microservices.We show that allocating fixed resources does not work well for different workloads for video analytics pipelines. We also show that Kubernetes’ VPA in conjunction with HPA does not work well for varying application workloads. As a remedy to this problem, in this paper, we propose DataX AutoScaleUp, which performs efficiently scaling up of CPU resources allocated to microservices in video analytics pipelines while Kubernetes’ HPA is operational. DataX AutoScaleUp uses novel techniques to adjust the allocated computing resources to different microservices in video analytics pipelines to improve overall application performance. Through real-world video analytics applications like Face Recognition and Human Attributes, we show that DataX AutoScaleUp can achieve up to 1.45X improvement in application processing rate when compared to alternative approaches with fixed CPU allocation and dynamic CPU allocation using VPA.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 68, 584-591
Scale Up while Scaling Out Microservices in Video Analytics Pipelines
Modern video analytics applications comprise multiple microservices chained together as pipelines and executed on container orchestration platforms like Kubernetes. Kubernetes automatically handles the scaling of these microservices for efficient application execution. There are two popular choices for scaling microservices in Kubernetes i.e. scaling Out using Horizontal Pod Autoscaler (HPA) and scaling Up using Vertical Pod Autoscaler (VPA). Both these have been studied independently, but there isn’t much prior work studying the joint scaling of these two. This paper investigates joint scaling, i.e., scaling up while scaling out (HPA) is in action. In particular, we focus on scaling up CPU resources allocated to the application microservices.We show that allocating fixed resources does not work well for different workloads for video analytics pipelines. We also show that Kubernetes’ VPA in conjunction with HPA does not work well for varying application workloads. As a remedy to this problem, in this paper, we propose DataX AutoScaleUp, which performs efficiently scaling up of CPU resources allocated to microservices in video analytics pipelines while Kubernetes’ HPA is operational. DataX AutoScaleUp uses novel techniques to adjust the allocated computing resources to different microservices in video analytics pipelines to improve overall application performance. Through real-world video analytics applications like Face Recognition and Human Attributes, we show that DataX AutoScaleUp can achieve up to 1.45X improvement in application processing rate when compared to alternative approaches with fixed CPU allocation and dynamic CPU allocation using VPA.
- Open Access
Deep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming
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 fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression is typically employed to eliminate unnecessary redundancies within and between video frames, thereby reducing the required bandwidth for video transmission. The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP). Poor choices of encoder parameters can result in reduced bandwidth efficiency and high likelihood of non-conformance. Non-conformance refers to the violation of the peak signal-to-noise ratio (PSNR) constraint for an encoded video segment. To address these issues, a real-time deep learning-based H.264 controller is proposed. This controller dynamically estimates the optimal encoder parameters based on the content of a video chunk with minimal delay. The objective is to maintain video quality in terms of PSNR above a specified threshold while minimizing the average bitrate of the compressed video. Experimental results, conducted on both QCIF dataset and a diverse range of random videos from public datasets, validate the effectiveness of this approach. Notably, it achieves improvements of up to 2.5 times in average bandwidth usage compared to the state-of-the-art adaptive bitrate video streaming, with a negligible non-conformance probability below $10^{-2}$.Open AccessDeep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming
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 fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression is typically employed to eliminate unnecessary redundancies within and between video frames, thereby reducing the required bandwidth for video transmission. The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP). Poor choices of encoder parameters can result in reduced bandwidth efficiency and high likelihood of non-conformance. Non-conformance refers to the violation of the peak signal-to-noise ratio (PSNR) constraint for an encoded video segment. To address these issues, a real-time deep learning-based H.264 controller is proposed. This controller dynamically estimates the optimal encoder parameters based on the content of a video chunk with minimal delay. The objective is to maintain video quality in terms of PSNR above a specified threshold while minimizing the average bitrate of the compressed video. Experimental results, conducted on both QCIF dataset and a diverse range of random videos from public datasets, validate the effectiveness of this approach. Notably, it achieves improvements of up to 2.5 times in average bandwidth usage compared to the state-of-the-art adaptive bitrate video streaming, with a negligible non-conformance probability below $10^{-2}$.