6 citations · 23 across the 17 of their papers we have counts for
18 papers
Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication
Yafan Huang, Guanpeng Li
We propose PaRID (PaRallel Instruction Duplication), a software-directed soft error detection framework that requires only compile-time effort for multithreading parallel programs.…
V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory
Dingyi Kang, Dongming Jiang, Yi Li +2
Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either. Yet most agent memories are…
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
Yafan Huang, Sheng Di, Guanpeng Li
Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through diverse perspectives such as cod…
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Dongming Jiang, Yi Li, Guanpeng Li +2
Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However…
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
Songtao Wei, Yi Li, Zhikai Li +7
Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajec…
CoSA: Compressed Sensing-Based Adaptation of Large Language Models
Songtao Wei, Yi Li, Bohan Zhang +6
Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most existing approaches, such…
MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
Dongming Jiang, Yi Li, Guanpeng Li +1
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity…
GPZ: GPU-Accelerated Lossy Compressor for Particle Data
Ruoyu Li, Yafan Huang, Longtao Zhang +10
Particle-based simulations and point-cloud applications generate massive, irregular datasets that challenge storage, I/O, and real-time analytics. Traditional compression technique…
YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training
Yi Li, Zhichun Guo, Guanpeng Li +1
Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains. During training stage, sampling plays an important role in reducin…
HoSZp: An Efficient Homomorphic Error-bounded Lossy Compressor for Scientific Data
Tripti Agarwal, Sheng Di, Jiajun Huang +7
Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific appli…
A Survey on Error-Bounded Lossy Compression for Scientific Datasets
Sheng Di, Jinyang Liu, Kai Zhao +23
Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving the reconstructed data fidelity very well. Many error…
cuSZ-: High-Ratio Scientific Lossy Compression on GPUs with Optimized Multi-Level Interpolation
Jinyang Liu, Jiannan Tian, Shixun Wu +10
Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes. Compared to CPU-based compressors, GPU-based compressors exhibit substan…
Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks
Pritam Dash, Guanpeng Li, Mehdi Karimibiuki +1
Sensors are crucial for perception and autonomous operation in robotic vehicles (RV). Unfortunately, RV sensors can be compromised by physical attacks such as sensor tampering or s…
COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
Sian Jin, Chengming Zhang, Xintong Jiang +5
Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory because the intermediate activation data must be saved in the memory during…
LCFI: A Fault Injection Tool for Studying Lossy Compression Error Propagation in HPC Programs
Baodi Shan, Aabid Shamji, Jiannan Tian +2
Error-bounded lossy compression is becoming more and more important to today's extreme-scale HPC applications because of the ever-increasing volume of data generated because it has…
A Novel Memory-Efficient Deep Learning Training Framework via Error-Bounded Lossy Compression
Sian Jin, Guanpeng Li, Shuaiwen Leon Song +1
Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN mode…
TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
Zitao Chen, Niranjhana Narayanan, Bo Fang +3
As machine learning (ML) has seen increasing adoption in safety-critical domains (e.g., autonomous vehicles), the reliability of ML systems has also grown in importance. While prio…
A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
Zitao Chen, Guanpeng Li, Karthik Pattabiraman
The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns. A prominent example is hardware transient faults that are growin…