6 citations · 21 across the 34 of their papers we have counts for
38 papers
PhysWAM: Physically Consistent World Action Model for Autonomous Driving
Dhruv Parikh, Fengcheng Yu, Quankai Gao +11
World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constr…
Accurate and Resource-Efficient Federated Continual Learning
Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan +2
Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability. Existing FC…
Can Graphs Help Vision SSMs See Better?
Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan +3
Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation…
TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks
Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna
Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning. In this paper, we identify an…
Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
Nikunj Gupta, James Zachary Hare, Jesse Milzman +2
Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on go…
ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models
Dhruv Parikh, Haoyang Fan, Rajgopal Kannan +1
Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens. Existing token reduction methods typically exploit \textit{either…
FAME: FPGA Acceleration of Secure Matrix Multiplication with Homomorphic Encryption
Zhihan Xu, Rajgopal Kannan, Viktor K. Prasanna
Homomorphic Encryption (HE) enables secure computation on encrypted data, addressing privacy concerns in cloud computing. However, the high computational cost of HE operations, par…
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
Ömer Faruk Akgül, Yusuf Hakan Kalaycı, Rajgopal Kannan +2
Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have e…
HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning
Nikunj Gupta, Bill Guo, Rajgopal Kannan +1
Large Language Models (LLMs) deliver state-of-the-art performance across many tasks but impose high computational and memory costs, limiting their deployment in resource-constraine…
TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations
Nikunj Gupta, Ludwika Twardecka, James Zachary Hare +3
In this paper, we propose capturing and utilizing \textit{Temporal Information through Graph-based Embeddings and Representations} or \textbf{TIGER} to enhance multi-agent reinforc…
Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan +1
Open-source Large Language Models (LLMs) increasingly specialize by domain (e.g., math, code, general reasoning), motivating systems that leverage complementary strengths across mo…
AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs
Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna
Matricized Tensor Times Khatri-Rao Product (MTTKRP) is the computational bottleneck in sparse tensor decomposition. As real-world sparse tensors grow to billions of nonzeros, they…
RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion
Ömer Faruk Akgül, Feiyu Zhu, Yuxin Yang +2
Temporal Knowledge Graphs (TKGs) represent dynamic facts as timestamped relations between entities. TKG completion involves forecasting missing or future links, requiring models to…
Adversarial Knapsack for Sequential Competitive Resource Allocation
Omkar Thakoor, Rajgopal Kannan, Victor Prasanna
This work addresses competitive resource allocation in a sequential setting, where two players allocate resources across objects or locations of shared interest. Departing from the…
Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning
Nikunj Gupta, James Zachary Hare, Jesse Milzman +2
This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations encode loca…
ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning
Dhruv Parikh, Jacob Fein-Ashley, Tian Ye +2
Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have dominated the field of Computer Vision (CV). Graph Neural Networks (GNN) have performed remarkably well acros…
Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours
Yuxin Yang, Hongkuan Zhou, Rajgopal Kannan +1
Temporal Graph Neural Networks (TGNNs) have emerged as powerful tools for modeling dynamic interactions across various domains. The design space of TGNNs is notably complex, given…
Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
Tian Ye, Rajgopal Kannan, Viktor Prasanna
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled d…
Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information
Ömer Faruk Akgül, Rajgopal Kannan, Viktor Prasanna
Graphs play a crucial role in data mining and machine learning, representing real-world objects and interactions. As graph datasets grow, managing large, decentralized subgraphs be…
Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
Gangda Deng, Hongkuan Zhou, Rajgopal Kannan +1
Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs). Increasing the GNN depth can expand the scope (i.e., receptive fiel…
Studying the Effects of Self-Attention on SAR Automatic Target Recognition
Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna
Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often stru…
Sparse MTTKRP Acceleration for Tensor Decomposition on GPU
Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna
Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the bottleneck kernel of sparse tensor decomposition. In this work, we propose a GPU-based algorithm design to addre…
Accelerating ViT Inference on FPGA through Static and Dynamic Pruning
Dhruv Parikh, Shouyi Li, Bingyi Zhang +3
Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied t…
GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Bingyi Zhang, Rajgopal Kannan, Carl Busart +1
Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers…