Showing 1–14 of 14 results for author: Selvam, S

Eval-Pair Matrix: Answer-Paired Meta-Evaluation of LLM Judges for Grounded RAG

Authors: Sriram Selvam, Anneswa Ghosh

Abstract: LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, ge… ▽ More LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, generate answers from perturbed passages with GPT, Grok, and Gemini models, and then use the same models as blind judges to evaluate each answer against the original passages. The experiment contains 300 core records, 897 labeled generator outputs, and 2,683 judge verdicts in a crossed 3 x 3 matrix; the primary analysis uses 275 fully validated records. Instead of comparing diagonal and off-diagonal cells across different answers, we estimate same-model effects by pairing judges on the exact same candidate answer. This changes the interpretation: diagonal and off diagonal F1 are similar, and the paired same-model recall effect is near zero (-0.5 pp; 95% cluster bootstrap CI [-2.7, +1.7]). The only robust paired gap is lower matching-judge flagging for answers that avoided the induced claim (-4.3 pp). A targeted human evaluation finds that reviewed apparent false positives are alternate source-error detections, mistakes in labeling whether the induced claim was adopted, or unclear cases; none were adjudicated as genuine false alarms. The lesson is methodological: RAG judge studies should report full matrices, answer-paired effects, behavior strata, and label-task alignment. △ Less

Submitted 12 July, 2026; originally announced July 2026.

Equal Accuracy, Unequal Evidence: Search APIs as Decision Surfaces for Tool-Using Agents

Authors: Sriram Selvam, Anneswa Ghosh

Abstract: Search APIs are the fundamental retrieval layer for many agents and are often their most frequently used tool. Traditional search APIs provide URLs, titles, and snippets that preview website contents. Because full-page retrieval is token-intensive, agent retrieval architectures increasingly use progressive disclosure: the agent first sees snippets and then chooses whether to fetch full pages. In s… ▽ More Search APIs are the fundamental retrieval layer for many agents and are often their most frequently used tool. Traditional search APIs provide URLs, titles, and snippets that preview website contents. Because full-page retrieval is token-intensive, agent retrieval architectures increasingly use progressive disclosure: the agent first sees snippets and then chooses whether to fetch full pages. In such systems, search API performance is often evaluated primarily by answer accuracy. We argue that a commercial search API is better understood as a decision surface: the ranked snippets, URLs, and metadata that determine whether an agent answers immediately, searches again, or spends tokens opening pages. We test this claim with one frozen GPT-5.4 agent, two tools (search_web and fetch_page), and 100 questions from SEALQA-HARD, varying only the search provider (Brave, Tavily, Firecrawl). A Kimi-K2.6 oracle labels every content element visible to the agent (URL, title, snippet, and fetched page, when fetched), producing 6,869 valid per-URL judgments. We use an audited correct-answer label, semantic match, which preserves exact matches while accepting harmless formatting and naming variants. Under this measure, the providers remain close (25, 25, 26 / 100), but their evidence economies differ sharply: Brave offers gold-answer-rich snippets, Tavily concentrates gold-supporting URLs at rank 1, and Firecrawl is associated with broader exploration under this fixed agent policy. We also introduce a surface contradiction-to-gold URL ratio, which varies from 0.92 to 2.59. Provider choice is therefore a retrieval-budget and policy decision, not merely a recall decision. △ Less

Submitted 11 July, 2026; originally announced July 2026.

ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent

Authors: Sriram Selvam, Anneswa Ghosh

Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present PROF… ▽ More Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present PROFILEFOUNDRY, a deterministic generator and fixed reference release of 100,000 adult synthetic Person Objects across eight locales. Each object combines a typed current snapshot, household, family, and employer links, snapshot-aligned events, normalized relational views, and generation provenance. The release contains 709,228 events, 40,338 households, 52,491 employers, and 518,564 directed relationship edges. We report evidence in separate categories: selected population-marginal comparisons, per-object invariant checks, release-wide referential and temporal closure, and coincidence/provenance screens. PROFILEFOUNDRY is not a population-fidelity model, a rendered-text corpus, or a formal privacy mechanism. Instead, it is a responsible synthetic source layer for constructing downstream foundation-model evaluations involving memory, privacy, document understanding, record linkage, and agent state while keeping the synthetic person behind each artifact inspectable △ Less

Submitted 24 June, 2026; originally announced June 2026.

QASM: A Novel Framework for QUIC-Aware Stateful Middleboxes

Authors: Hari Hara Sudhan Selvam, Sameer G. Kulkarni

Abstract: Stateful Middleboxes are integral part of enterprise and campus networks that provide essential in-network, security, and value-added services. These stateful middleboxes rely on precise network flow identification. However, the adoption of HTTP/3, which uses the QUIC protocol, poses significant challenges to the proper functioning of these devices. QUIC's encryption and connection migration featu… ▽ More Stateful Middleboxes are integral part of enterprise and campus networks that provide essential in-network, security, and value-added services. These stateful middleboxes rely on precise network flow identification. However, the adoption of HTTP/3, which uses the QUIC protocol, poses significant challenges to the proper functioning of these devices. QUIC's encryption and connection migration features obscure flow semantics, disrupting middlebox visibility and functionality. We examine how QUIC disrupts middleboxes like Network Address Translators (NATs), Rate Limiters, Load Balancers, etc., and affects Kubernetes-based service deployments. To address these challenges, we propose a novel, generalized framework that enables stateful middleboxes to reliably track QUIC connections, even when the endpoints change their internet protocol (IP) address or port numbers. Our prototype implementation demonstrates that the proposed approach preserves middlebox functionality with HTTP/3 with negligible performance overhead (< 5%) on both throughput and latency, and works effectively even under high QUIC connection migration rates of up to 100 Hz. △ Less

Submitted 3 February, 2026; originally announced February 2026.

KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models

Authors: Sourjya Roy, Shrihari Sridharan, Surya Selvam, Anand Raghunathan

Abstract: As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding dimension, often exceeding the memory footprint of the model itself and limiting achievable batch sizes and context windows. To address this challenge, we presen… ▽ More As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding dimension, often exceeding the memory footprint of the model itself and limiting achievable batch sizes and context windows. To address this challenge, we present KV CAR, a unified and architecture agnostic framework that significantly reduces KV cache storage while maintaining model fidelity. KV CAR combines two complementary techniques. First, a lightweight autoencoder learns compact representations of key and value tensors along the embedding dimension, compressing them before they are stored in the KV cache and restoring them upon retrieval. Second, a similarity driven reuse mechanism identifies opportunities to reuse KV tensors of specific attention heads across adjacent layers. Together, these methods reduce the dimensional and structural redundancy in KV tensors without requiring changes to the transformer architecture. Evaluations on GPT 2 and TinyLLaMA models across Wikitext, C4, PIQA, and Winogrande datasets demonstrate that KV CAR achieves up to 47.85 percent KV cache memory reduction with minimal impact on perplexity and zero shot accuracy. System level measurements on an NVIDIA A40 GPU show that the reduced KV footprint directly translates into longer sequence lengths and larger batch sizes during inference. These results highlight the effectiveness of KV CAR in enabling memory efficient LLM inference. △ Less

Submitted 7 December, 2025; originally announced December 2025.

TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection

Authors: Xinqi Xiong, Prakrut Patel, Qingyuan Fan, Amisha Wadhwa, Sarathy Selvam, Xiao Guo, Luchao Qi, Xiaoming Liu, Roni Sengupta

Abstract: The rapid advancement of talking-head deepfake generation fueled by advanced generative models has elevated the realism of synthetic videos to a level that poses substantial risks in domains such as media, politics, and finance. However, current benchmarks for deepfake talking-head detection fail to reflect this progress, relying on outdated generators and offering limited insight into model robus… ▽ More The rapid advancement of talking-head deepfake generation fueled by advanced generative models has elevated the realism of synthetic videos to a level that poses substantial risks in domains such as media, politics, and finance. However, current benchmarks for deepfake talking-head detection fail to reflect this progress, relying on outdated generators and offering limited insight into model robustness and generalization. We introduce TalkingHeadBench, a comprehensive multi-model multi-generator benchmark and curated dataset designed to evaluate the performance of state-of-the-art detectors on the most advanced generators. Our dataset includes deepfakes synthesized by leading academic and commercial models and features carefully constructed protocols to assess generalization under distribution shifts in identity and generator characteristics. We benchmark a diverse set of existing detection methods, including CNNs, vision transformers, and temporal models, and analyze their robustness and generalization capabilities. In addition, we provide error analysis using Grad-CAM visualizations to expose common failure modes and detector biases. TalkingHeadBench is hosted on https://huggingface.co/datasets/luchaoqi/TalkingHeadBench with open access to all data splits and protocols. Our benchmark aims to accelerate research towards more robust and generalizable detection models in the face of rapidly evolving generative techniques. △ Less

Submitted 20 January, 2026; v1 submitted 30 May, 2025; originally announced May 2025.

Comments: WACV2026

PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs

Authors: Sriram Selvam, Anneswa Ghosh

Abstract: The memorization of sensitive and personally identifiable information (PII) by large language models (LLMs) poses growing privacy risks as models scale and are increasingly deployed in real-world applications. Existing efforts to study sensitive and PII data memorization and develop mitigation strategies are hampered by the absence of comprehensive, realistic, and ethically sourced datasets reflec… ▽ More The memorization of sensitive and personally identifiable information (PII) by large language models (LLMs) poses growing privacy risks as models scale and are increasingly deployed in real-world applications. Existing efforts to study sensitive and PII data memorization and develop mitigation strategies are hampered by the absence of comprehensive, realistic, and ethically sourced datasets reflecting the diversity of sensitive information found on the web. We introduce PANORAMA - Profile-based Assemblage for Naturalistic Online Representation and Attribute Memorization Analysis, a large-scale synthetic corpus of 384,789 samples derived from 9,674 synthetic profiles designed to closely emulate the distribution, variety, and context of PII and sensitive data as it naturally occurs in online environments. Our data generation pipeline begins with the construction of internally consistent, multi-attribute human profiles using constrained selection to reflect real-world demographics such as education, health attributes, financial status, etc. Using a combination of zero-shot prompting and OpenAI o3-mini, we generate diverse content types - including wiki-style articles, social media posts, forum discussions, online reviews, comments, and marketplace listings - each embedding realistic, contextually appropriate PII and other sensitive information. We validate the utility of PANORAMA by fine-tuning the Mistral-7B model on 1x, 5x, 10x, and 25x data replication rates with a subset of data and measure PII memorization rates - revealing not only consistent increases with repetition but also variation across content types, highlighting PANORAMA's ability to model how memorization risks differ by context. Our dataset and code are publicly available, providing a much-needed resource for privacy risk assessment, model auditing, and the development of privacy-preserving LLMs. △ Less

Submitted 18 May, 2025; originally announced May 2025.

Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approach

Authors: Srecharan Selvam

Abstract: Automating leaf manipulation in agricultural settings faces significant challenges, including the variability of plant morphologies and deformable leaves. We propose a novel hybrid geometric-neural approach for autonomous leaf grasping that combines traditional computer vision with neural networks through self-supervised learning. Our method integrates YOLOv8 for instance segmentation and RAFT-Ste… ▽ More Automating leaf manipulation in agricultural settings faces significant challenges, including the variability of plant morphologies and deformable leaves. We propose a novel hybrid geometric-neural approach for autonomous leaf grasping that combines traditional computer vision with neural networks through self-supervised learning. Our method integrates YOLOv8 for instance segmentation and RAFT-Stereo for 3D depth estimation to build rich leaf representations, which feed into both a geometric feature scoring pipeline and a neural refinement module (GraspPointCNN). The key innovation is our confidence-weighted fusion mechanism that dynamically balances the contribution of each approach based on prediction certainty. Our self-supervised framework uses the geometric pipeline as an expert teacher to automatically generate training data. Experiments demonstrate that our approach achieves an 88.0% success rate in controlled environments and 84.7% in real greenhouse conditions, significantly outperforming both purely geometric (75.3%) and neural (60.2%) methods. This work establishes a new paradigm for agricultural robotics where domain expertise is seamlessly integrated with machine learning capabilities, providing a foundation for fully automated crop monitoring systems. △ Less

Submitted 16 May, 2025; v1 submitted 6 May, 2025; originally announced May 2025.

Comments: 15 pages, 9 figures

ACM Class: I.2.10

T-REX: Vision-Based System for Autonomous Leaf Detection and Grasp Estimation

Authors: Srecharan Selvam, Abhisesh Silwal, George Kantor

Abstract: T-Rex (The Robot for Extracting Leaf Samples) is a gantry-based robotic system developed for autonomous leaf localization, selection, and grasping in greenhouse environments. The system integrates a 6-degree-of-freedom manipulator with a stereo vision pipeline to identify and interact with target leaves. YOLOv8 is used for real-time leaf segmentation, and RAFT-Stereo provides dense depth maps, all… ▽ More T-Rex (The Robot for Extracting Leaf Samples) is a gantry-based robotic system developed for autonomous leaf localization, selection, and grasping in greenhouse environments. The system integrates a 6-degree-of-freedom manipulator with a stereo vision pipeline to identify and interact with target leaves. YOLOv8 is used for real-time leaf segmentation, and RAFT-Stereo provides dense depth maps, allowing the reconstruction of 3D leaf masks. These observations are processed through a leaf grasping algorithm that selects the optimal leaf based on clutter, visibility, and distance, and determines a grasp point by analyzing local surface flatness, top-down approachability, and margin from edges. The selected grasp point guides a trajectory executed by ROS-based motion controllers, driving a custom microneedle-equipped end-effector to clamp the leaf and simulate tissue sampling. Experiments conducted with artificial plants under varied poses demonstrate that the T-Rex system can consistently detect, plan, and perform physical interactions with plant-like targets, achieving a grasp success rate of 66.6\%. This paper presents the system architecture, implementation, and testing of T-Rex as a step toward plant sampling automation in Controlled Environment Agriculture (CEA). △ Less

Submitted 2 May, 2025; originally announced May 2025.

Comments: 11 Pages, 10 figures, 2 tables

ACM Class: I.2.10

Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platforms

Authors: Shrihari Sridharan, Surya Selvam, Kaushik Roy, Anand Raghunathan

Abstract: Event cameras have emerged as a promising sensing modality for autonomous navigation systems, owing to their high temporal resolution, high dynamic range and negligible motion blur. To process the asynchronous temporal event streams from such sensors, recent research has shown that a mix of Artificial Neural Networks (ANNs), Spiking Neural Networks (SNNs) as well as hybrid SNN-ANN algorithms are n… ▽ More Event cameras have emerged as a promising sensing modality for autonomous navigation systems, owing to their high temporal resolution, high dynamic range and negligible motion blur. To process the asynchronous temporal event streams from such sensors, recent research has shown that a mix of Artificial Neural Networks (ANNs), Spiking Neural Networks (SNNs) as well as hybrid SNN-ANN algorithms are necessary to achieve high accuracies across a range of perception tasks. However, we observe that executing such workloads on commodity edge platforms which feature heterogeneous processing elements such as CPUs, GPUs and neural accelerators results in inferior performance. This is due to the mismatch between the irregular nature of event streams and diverse characteristics of algorithms on the one hand and the underlying hardware platform on the other. We propose Ev-Edge, a framework that contains three key optimizations to boost the performance of event-based vision systems on edge platforms: (1) An Event2Sparse Frame converter directly transforms raw event streams into sparse frames, enabling the use of sparse libraries with minimal encoding overheads (2) A Dynamic Sparse Frame Aggregator merges sparse frames at runtime by trading off the temporal granularity of events and computational demand thereby improving hardware utilization (3) A Network Mapper maps concurrently executing tasks to different processing elements while also selecting layer precision by considering both compute and communication overheads. On several state-of-art networks for a range of autonomous navigation tasks, Ev-Edge achieves 1.28x-2.05x improvements in latency and 1.23x-2.15x in energy over an all-GPU implementation on the NVIDIA Jetson Xavier AGX platform for single-task execution scenarios. Ev-Edge also achieves 1.43x-1.81x latency improvements over round-robin scheduling methods in multi-task execution scenarios. △ Less

Submitted 23 March, 2024; originally announced March 2024.

FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays

Authors: Surya Selvam, Vinod Ganesan, Pratyush Kumar

Abstract: Both efficient neural networks and hardware accelerators are being explored to speed up DNN inference on edge devices. For example, MobileNet uses depthwise separable convolution to achieve much lower latency, while systolic arrays provide much higher performance per watt. Interestingly however, the combination of these two ideas is inefficient: The computational patterns of depth-wise separable c… ▽ More Both efficient neural networks and hardware accelerators are being explored to speed up DNN inference on edge devices. For example, MobileNet uses depthwise separable convolution to achieve much lower latency, while systolic arrays provide much higher performance per watt. Interestingly however, the combination of these two ideas is inefficient: The computational patterns of depth-wise separable convolution are not systolic and lack data reuse to saturate the systolic array's constrained dataflow. In this paper, we propose FuSeConv (Fully-Separable Convolution) as a drop-in replacement for depth-wise separable convolution. FuSeConv generalizes the decomposition of convolutions fully to separable 1D convolutions along spatial and depth dimensions. The resultant computation is systolic and efficiently utilizes the systolic array with a slightly modified dataflow. With FuSeConv, we achieve a significant speed-up of 3x-7x with the MobileNet family of networks on a systolic array of size 64x64, with comparable accuracy on the ImageNet dataset. The high speed-up motivates exploration of hardware-aware Neural Operator Search (NOS) in complement to ongoing efforts on Neural Architecture Search (NAS). △ Less

Submitted 27 May, 2021; originally announced May 2021.

Comments: To appear in the Proceedings of the Design, Automation & Test in Europe (DATE), 2021

Circuit Complexity From Supersymmetric Quantum Field Theory With Morse Function

Authors: Sayantan Choudhury, Sachin Panneer Selvam, K. Shirish

Abstract: Computation of circuit complexity has gained much attention in the Theoretical Physics community in recent times to gain insights into the chaotic features and random fluctuations of fields in the quantum regime. Recent studies of circuit complexity take inspiration from Nielsen's geometric approach, which is based on the idea of optimal quantum control in which a cost function is introduced for t… ▽ More Computation of circuit complexity has gained much attention in the Theoretical Physics community in recent times to gain insights into the chaotic features and random fluctuations of fields in the quantum regime. Recent studies of circuit complexity take inspiration from Nielsen's geometric approach, which is based on the idea of optimal quantum control in which a cost function is introduced for the various possible path to determine the optimum circuit. In this paper, we study the relationship between the circuit complexity and Morse theory within the framework of algebraic topology, which will then help us study circuit complexity in supersymmetric quantum field theory describing both simple and inverted harmonic oscillators up to higher orders of quantum corrections. We will restrict ourselves to $\mathcal{N} = 1$ supersymmetry with one fermionic generator $Q_α$. The expression of circuit complexity in quantum regime would then be given by the Hessian of the Morse function in supersymmetric quantum field theory. We also provide technical proof of the well known universal connecting relation between quantum chaos and circuit complexity of the supersymmetric quantum field theories, using the general description of Morse theory. △ Less

Submitted 11 August, 2022; v1 submitted 25 January, 2021; originally announced January 2021.

Comments: 41 pages, 10 figures, 4 tables, This project is the part of the non-profit virtual international research consortium "Quantum Aspects of Space-Time and Matter (QASTM)", Revised version, References and some of the explanations elaborated and updated, Accepted for publication in Symmetry

Journal ref: Symmetry 14 (2022) no. 8, 1656

Human Error in IT Security

Authors: Visahl Samson David Selvam

Abstract: This paper details on the analysis of human error, an IT security issue, and a major threat to the company. The human is one of the weakest links in the cybersecurity chain however it is a fundamental constituent of the embodiment. This report provides a sophisticated elucidation on the various human errors and the necessary measures to mitigate and control the menacing IT security issue. This paper details on the analysis of human error, an IT security issue, and a major threat to the company. The human is one of the weakest links in the cybersecurity chain however it is a fundamental constituent of the embodiment. This report provides a sophisticated elucidation on the various human errors and the necessary measures to mitigate and control the menacing IT security issue. △ Less

Submitted 8 May, 2020; originally announced May 2020.

Processor Based Active Queue Management for providing QoS in Multimedia Application

Authors: N. Saravana Selvam, S. Radhakrishnan

Abstract: The objective of this paper is to implement the Active Network based Active Queue Management Technique for providing Quality of Service (QoS) using Network Processor(NP) based router to enhance multimedia applications. The performance is evaluated using Intel IXP2400 NP Simulator. The results demonstrate that, Active Network based Active Queue Management has better performance than RED algorithm i… ▽ More The objective of this paper is to implement the Active Network based Active Queue Management Technique for providing Quality of Service (QoS) using Network Processor(NP) based router to enhance multimedia applications. The performance is evaluated using Intel IXP2400 NP Simulator. The results demonstrate that, Active Network based Active Queue Management has better performance than RED algorithm in case of congestion and is well suited to achieve high speed packet classification to support multimedia applications with minimum delay and Queue loss. Using simulation, we show that the proposed system can provide assurance for prioritized flows with improved network utilization where bandwidth is shared among the flows according to the levels of priority. We first analyze the feasibility and optimality of the load distribution schemes and then present separate solutions for non-delay sensitive streams and delay-sensitive streams. Rigorous simulations and experiments have been carried out to evaluate the performance. △ Less

Submitted 10 April, 2010; originally announced April 2010.

Comments: IEEE Publication format, International Journal of Computer Science and Information Security, IJCSIS, Vol. 7 No. 3, March 2010, USA. ISSN 1947 5500, http://sites.google.com/site/ijcsis/