11 citations · 24 across the 41 of their papers we have counts for
46 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…
FPGA Acceleration of Fully Homomorphic Encryption with Adaptive Key Switching
Zhihan Xu, Jayashree Adivarahan, Rajgopal Kannan +1
Fully Homomorphic Encryption (FHE) enables privacy-preserving cloud services but incurs substantial computation overhead, making hardware acceleration essential. Among FHE operatio…
FOLIO: Focused Semantic Memory for Streaming Video Understanding
Haoyang Fan, Dhruv Parikh, Anvitha Ramachandran +4
In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without bound, the system must cont…
Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics
Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan +2
State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal sequence modeling. While effect…
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…
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
Nikunj Gupta, James Zachary Hare, Jesse Milzman +2
Cooperative multi-agent reinforcement learning agents that act on partial local observations face a fundamental information bottleneck: the knowledge needed to select jointly optim…
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…
Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
Ömer Faruk Akgül, Rajgopal Kannan, Willie Neiswanger +1
Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redist…
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…
Do LLM-derived graph priors improve multi-agent coordination?
Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna
Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (M…
Latent Denoising Improves Visual Alignment in Large Multimodal Models
Dhruv Parikh, Jacob Fein-Ashley, Rajgopal Kannan +1
Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This of…
A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA
Neelesh Gupta, Peter Wang, Rajgopal Kannan +1
Gated DeltaNet (GDN) is a linear attention mechanism that replaces the growing KV cache with a fixed-size recurrent state. Hybrid LLMs like Qwen3-Next use 75% GDN layers and achiev…
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
Gangda Deng, Zhaoling Chen, Zhongming Yu +11
Real-world software must continuously evolve to meet ever-changing and open-ended requirements. AI agents, increasingly deployed as long-running systems, are now entrusted to drive…
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…
Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
Gangda Deng, Yuxin Yang, Ömer Faruk Akgül +4
Graph Neural Networks (GNNs) have become essential tools for learning on relational data, yet the performance of a single GNN is often limited by the heterogeneity present in real-…
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…