9 papers
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran +3
This paper presents GraphMend, a compiler technique that automatically fixes FX graph breaks in PyTorch 2 programs. Although PyTorch 2 introduced TorchDynamo and TorchInductor to e…
Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
Joshua Brodsky, Dhravid Kumar, Savini Kashmira +4
Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolut…
Evaluation of Prompt Injection Defenses in Large Language Models
Priyal Deep, Shane Emmons, Amy Fox +4
LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hu…
BlazingAML: High-Throughput Anti-Money Laundering (AML) via Multi-Stage Graph Mining
Haojie Ye, Arjun Laxman, Yichao Yuan +2
Money laundering detection faces challenges due to excessive false positives and inadequate adaptation to sophisticated multi-stage schemes that exploit modern financial networks.…
Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering
Jayanaka L. Dantanarayana, Savini Kashmira, Thakee Nathees +4
AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Program…
TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG
Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky +5
Retrieval-Augmented Generation (RAG) is one of the leading and most widely used techniques for enhancing LLM retrieval capabilities, but it still faces significant limitations in c…