VP
Viktor K. Prasanna
cs.LGcs.DCcs.ARcs.CVcs.AIeess.IVcs.CLcs.PFstat.MLcs.CR
On Valency
published · living versionsW_7qkdycta·v1 · currentpublished
Topology Survives Shuffling: Robust Long-Context Memory Access Prediction for Graph Analytics
with Dongyan Sun, Neelesh Gupta, Rajgopal Kannan
1 version
Preprints & journals
113 papers in the corpus · 2006–2026FPGA Acceleration of Fully Homomorphic Encryption with Adaptive Key Switching2609.09423v1 · Zhihan Xu, Jayashree Adivarahan, Rajgopal Kannan et al.2026 · 0 citationsarXiv
FOLIO: Focused Semantic Memory for Streaming Video Understanding2607.13298v1 · Haoyang Fan, Dhruv Parikh, Anvitha Ramachandran et al.2026 · 0 citationsarXiv
Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics2607.03589v2 · Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan et al.2026 · 0 citationsarXiv
Accurate and Resource-Efficient Federated Continual Learning2606.11480v1 · Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan et al.2026 · 0 citationsarXiv
Can Graphs Help Vision SSMs See Better?2605.11300v1 · Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan et al.2026 · 0 citationsarXiv
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning2605.08391v2 · Nikunj Gupta, James Zachary Hare, Jesse Milzman et al.2026 · 0 citationsarXiv
Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning2605.06241v3 · Omer Faruk Akgul, Rajgopal Kannan, Willie Neiswanger et al.2026 · 0 citationsarXiv
TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks2604.27356v1 · Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna2026 · 0 citationsarXiv
ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing2604.21280v1 · Jebacyril Arockiaraj, Dhruv Parikh, Viktor Prasanna2026 · 1 citationarXiv
GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA2604.21290v1 · Anvitha Ramachandran, Dhruv Parikh, Viktor Prasanna2026 · 0 citationsarXiv
Do LLM-derived graph priors improve multi-agent coordination?2604.17191v1 · Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna2026 · 0 citationsarXiv
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution2603.13428v4 · Gangda Deng, Zhaoling Chen, Zhongming Yu et al.2026 · 0 citationsarXiv
A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA2603.05931v1 · Neelesh Gupta, Peter Wang, Rajgopal Kannan et al.2026 · 0 citationsarXiv
Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning2602.17009v2 · Nikunj Gupta, James Zachary Hare, Jesse Milzman et al.2026 · 0 citationsarXiv
System-Level Performance Modeling of Photonic In-Memory Computing2602.00892v1 · Jebacyril Arockiaraj, Sasindu Wijeratne, Sugeet Sunder et al.2026 · 1 citationarXiv
Primitive-Driven Acceleration of Hyperdimensional Computing for Real-Time Image Classification2601.20061v1 · Dhruv Parikh, Jebacyril Arockiaraj, Viktor Prasanna2026 · 0 citationsarXiv
Enabling Long FFT Convolutions on Memory-Constrained FPGAs via Chunking2601.06065v1 · Peter Wang, Neelesh Gupta, Viktor Prasanna2025 · 0 citationsarXiv
FAME: FPGA Acceleration of Secure Matrix Multiplication with Homomorphic Encryption2512.15515v1 · Zhihan Xu, Rajgopal Kannan, Viktor K. Prasanna2025 · 0 citationsarXiv
Efficient and Accurate Graph Classification with Hyperdimensional Computing on FPGA2512.08089v2 · Jebacyril Arockiaraj, Dhruv Parikh, Viktor Prasanna2025 · 0 citationsarXiv
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning2512.05325v1 · Omer Faruk Akgul, Yusuf Hakan Kalaycı, Rajgopal Kannan et al.2025 · 0 citationsarXiv
HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning2511.09873v1 · Nikunj Gupta, Bill Guo, Rajgopal Kannan et al.2025 · 0 citationsarXiv
TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations2511.08832v1 · Nikunj Gupta, Ludwika Twardecka, James Zachary Hare et al.2025 · 0 citationsarXiv
Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study2510.18370v1 · Gangda Deng, Yuxin Yang, Omer Faruk Akgul et al.2025 · 0 citationsarXiv
Accelerating Dynamic Image Graph Construction on FPGA for Vision GNNs2509.25121v1 · Anvitha Ramachandran, Dhruv Parikh, Viktor Prasanna2025 · 1 citationarXiv
Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units2509.25155v2 · Neelesh Gupta, Rakshith Jayanth, Dhruv Parikh et al.2025 · 0 citationsarXiv
Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say2509.21164v1 · Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan et al.2025 · 0 citationsarXiv
AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs2507.15121v2 · Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna2025 · 1 citationarXiv
ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs2506.09282v1 · Dhruv Parikh, Viktor Prasanna2025 · 0 citationsarXiv
RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion2505.17794v1 · Omer Faruk Akgul, Feiyu Zhu, Yuxin Yang et al.2025 · 2 citationsarXiv
Predictive Performance of Photonic SRAM-based In-Memory Computing for Tensor Decomposition2503.18206v1 · Sasindu Wijeratne, Sugeet Sunder, Md Abdullah-Al Kaiser et al.2025 · 3 citationsarXiv
LocAgent: Graph-Guided LLM Agents for Code Localization2503.09089v2 · Zhaoling Chen, Xiangru Tang, Gangda Deng et al.2025 · 15 citationsarXiv
SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts2502.18394v7 · Jacob Fein-Ashley, Neelesh Gupta, Rajgopal Kannan et al.2025 · 1 citationarXiv
Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning2502.04028v3 · Nikunj Gupta, James Zachary Hare, Jesse Milzman et al.2025 · 1 citationarXiv
ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning2501.10640v2 · Dhruv Parikh, Jacob Fein-Ashley, Tian Ye et al.2025 · 8 citationsarXiv
Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours2412.20256v1 · Yuxin Yang, Hongkuan Zhou, Rajgopal Kannan et al.2024 · 0 citationsarXiv
Adversarial Training in Low-Label Regimes with Margin-Based Interpolation2411.17959v1 · Tian Ye, Rajgopal Kannan, Viktor Prasanna2024 · 0 citationsarXiv
Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information2410.14010v1 · Omer Faruk Akgul, Rajgopal Kannan, Viktor Prasanna2024 · 0 citationsarXiv
Benchmarking Edge AI Platforms for High-Performance ML Inference2409.14803v1 · Rakshith Jayanth, Neelesh Gupta, Viktor Prasanna2024 · 31 citationsarXiv
Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants2409.06998v4 · Gangda Deng, Hongkuan Zhou, Rajgopal Kannan et al.2024 · 0 citationsarXiv
Studying the Effects of Self-Attention on SAR Automatic Target Recognition2409.00473v1 · Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna2024 · 1 citationarXiv
Benchmarking the Performance of Large Language Models on the Cerebras Wafer Scale Engine2409.00287v2 · Zuoning Zhang, Dhruv Parikh, Youning Zhang et al.2024 · 5 citationsarXiv
Sparse MTTKRP Acceleration for Tensor Decomposition on GPU2405.08470v1 · Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna2024 · 6 citationsarXiv
GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA2404.07188v1 · Bingyi Zhang, Rajgopal Kannan, Carl Busart et al.2024 · 5 citationsarXiv
TabConv: Low-Computation CNN Inference via Table Lookups2404.05872v1 · Neelesh Gupta, Narayanan Kannan, Pengmiao Zhang et al.2024 · 6 citationsarXiv
VTR: An Optimized Vision Transformer for SAR ATR Acceleration on FPGA2404.04527v1 · Sachini Wickramasinghe, Dhruv Parikh, Bingyi Zhang et al.2024 · 8 citationsarXiv
FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification2404.03225v1 · Xu Wang, Tian Ye, Rajgopal Kannan et al.2024 · 4 citationsarXiv
Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks2403.18318v1 · Tian Ye, Rajgopal Kannan, Viktor Prasanna et al.2024 · 3 citationsarXiv
A Unified CPU-GPU Protocol for GNN Training2403.17092v1 · Yi-Chien Lin, Gangda Deng, Viktor Prasanna2024 · 10 citationsarXiv
Accelerating ViT Inference on FPGA through Static and Dynamic Pruning2403.14047v2 · Dhruv Parikh, Shouyi Li, Bingyi Zhang et al.2024 · 14 citationsarXiv
PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models2402.13441v1 · Neelesh Gupta, Pengmiao Zhang, Rajgopal Kannan et al.2024 · 4 citations2023 IEEE High Performance Extreme Computing Conference (HPEC), 2023, pp. 1-7
Career total: 1056 works. 113 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.