24 citations · 58 across the 50 of their papers we have counts for
55 papers
HandAnthro: Automated Hand Anthropometry from a Single Image
Fan Zhou, Shuairan Chen, Mengying Zhang +6
Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manual landmarking. We present HandA…
Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
Hung Phan, Waqwoya Abebe, Youssef Hussein +3
Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum-likelih…
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Mobina Kashaniyan, Ali Jannesari
Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often desc…
Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking
Md Arafat Hossain, Thomas Randall, Akash Dutta +3
As the complexity of High Performance Computing (HPC) ecosys- tems continually increases, achieving optimal performance becomes a challenge. Traditional performance autotuning tech…
APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning
Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou +2
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization addres…
Interpretable Adaptive Sampling for LLM Test-Time Scaling
Mobina Kashaniyan, Ali Jannesari
Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on eas…
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation
Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing…
VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs
Shahrzad Esmat, Dhawal Shah, Ali Jannesari
The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference. Two leading training-free families are both structurally limited: token…
POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation
Hung Phan, Aniroop Naladala, Dubey Avanindra +3
Recent large language models (LLMs) are good at general text generation, but it is still hard to use them for domain-specific data generation because the output must follow strict…
ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5
Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sust…
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previ…
LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
Shahrzad Esmat, Chaunte W. Lacewell, Sameh Gobriel +2
Retrieval systems underpin modern AI applications -- spanning visual search, recommendation engines, and multi-modal question answering. Modern multi-stage retrieval systems requir…
HeLoCo: Efficient asynchronous low-communication training under data and device heterogeneity
Abdullah Al Asif, Patrick Diem, Juan Pablo Muñoz +3
Distributed Low-Communication (DiLoCo) training reduces communication overhead by allowing workers to perform multiple local optimization steps before sending pseudo-gradients to a…
Fast MoE Inference via Predictive Prefetching and Expert Replication
Ankit Jyothish, Ali Jannesari, Aishwarya Sarkar +1
The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-specific expertise in LLMs and…
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
Md Anwar Hossen, Fatema Siddika, Juan Pablo Munoz +2
Large language models (LLMs) can learn new tasks through fine-tuning, but learning tasks sequentially often leads to catastrophic forgetting of earlier ones. This paper proposes CR…
NOMAD: Generating Embeddings for Massive Distributed Graphs
Aishwarya Sarkar, Sayan Ghosh, Nathan R. Tallent +1
Successful machine learning on graphs or networks requires embeddings that not only represent nodes and edges as low-dimensional vectors but also preserve the graph structure. Esta…
Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
Cunyang Wei, Siddharth Singh, Aishwarya Sarkar +7
Graph neural networks (GNNs) are widely used for learning on graph datasets derived from various real-world scenarios. Learning from extremely large graphs requires distributed tra…
ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms
Mohammad Pivezhandi, Mahdi Banisharif, Abusayeed Saifullah +1
Dynamic voltage and frequency scaling (DVFS) and task-to-core allocation are critical for thermal management and balancing energy and performance in embedded systems. Existing appr…
Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent +3
Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires f…
OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization
Arijit Bhattacharjee, Heng Ping, Son Vu Le +3
Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedb…
GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes
Mohammad Pivezhandi, Mahdi Banisharif, Saeed Bakhshan +2
Autonomous AI agents on embedded platforms require real-time, risk-aware scheduling under resource and thermal constraints. Classical heuristics struggle with workload irregularity…
Dynamic Detection of Inefficient Data Mapping Patterns in Heterogeneous OpenMP Applications
Luke Marzen, Junhyung Shim, Ali Jannesari
With the growing prevalence of heterogeneous computing, CPUs are increasingly being paired with accelerators to achieve new levels of performance and energy efficiency. However, da…
AgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search
Shahrzad Esmat, Mahdi Banisharif, Ali Jannesari
Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without di…
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previ…