8 citations · 16 across the 24 of their papers we have counts for
27 papers
LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound
Baixi Sun, Le Chen, Anjir Ahmed Chowdhury +10
Agent memory grows as agents read inputs, reason, and call tools. Longer histories increase inference cost and eventually exceed the context window. LLM-based summarization reduces…
FABRICA: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems
Yuebo Luo, Eliu Huerta, Venkatram Vishwanath +3
Porting GPU kernels across architectures requires architectural remapping, not syntax substitution. CUDA encodes decomposition, locality, and synchronization through threads, block…
LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks
Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang +4
Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost. We i…
HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
Yuebo Luo, Ahmad Sedigh Baroughi, Philip Stachura +4
Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring mon…
Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan +7
Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates int…
Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators
Shun Usami, Venkatram Vishwanath, E. Wes Bethel
As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge. While GPUs dominate…
Probabilistic Attribution For Large Language Models
Shilpika Shilpika, Carlo Graziani, Bethany Lusch +2
The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These prob…
Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System
Thang Duc Pham, Harikrishna Tummalapalli, Fakhrul Hasan Bhuiyan +5
The integration of Artificial Intelligence (AI) with High-Performance Computing (HPC) is transforming scientific workflows from human-directed pipelines into adaptive systems capab…
Swimba: Switch Mamba Model Scales State Space Models
Zhixu Du, Krishna Teja Chitty-Venkata, Murali Emani +3
Mixture-of-experts (MoE) is a common approach for increasing parameter capacity, but applying MoE to state space model (SSM) token mixers can multiply the cost of the recurrent sta…
Extending P: Spectral Conditions for Feature Learning Across Optimizers
Akshita Gupta, Marieme Ngom, Sam Foreman +1
Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance o…
Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins
Matthew Sinclair, Moeen Meigooni, Archit Vasan +14
Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80\% of cancer-related proteins contain lon…
FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access
Aditya Tanikanti, Benoit Côté, Yanfei Guo +9
We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FI…
Foundation Models for Discovery and Exploration in Chemical Space
Alexius Wadell, Anoushka Bhutani, Victor Azumah +26
Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing computational and experimental approaches…
AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
Väinö Hatanpää, Eugene Ku, Jason Stock +12
Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble…
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
Krishna Teja Chitty-Venkata, Jie Ye, Xian-He Sun +4
KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of…
LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference
Krishna Teja Chitty-Venkata, Sandeep Madireddy, Murali Emani +1
Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prio…
PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters
Krishu K Thapa, Reet Barik, Krishna Teja Chitty-Venkata +2
Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the…
Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery
William E. Allcock, Benjamin S. Allen, James Anchell +106
Aurora is Argonne National Laboratory's pioneering Exascale supercomputer, designed to accelerate scientific discovery with cutting-edge architectural innovations. Key new technolo…
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
Krishna Teja Chitty-Venkata, Sylvia Howland, Golara Azar +5
Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining c…
LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language Models
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath
Vision Language Models (VLMs) integrate visual and text modalities to enable multimodal understanding and generation. These models typically combine a Vision Transformer (ViT) as a…
AI Assistants to Enhance and Exploit the PETSc Knowledge Base
Barry Smith, Junchao Zhang, Hong Zhang +7
Generative AI, especially through large language models (LLMs), is transforming how technical knowledge can be accessed, reused, and extended. PETSc, a widely used numerical librar…
HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
Ozan Gokdemir, Carlo Siebenschuh, Alexander Brace +21
The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval Augm…
AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine
Carlo Siebenschuh, Kyle Hippe, Ozan Gokdemir +10
Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive…
BaKlaVa -- Budgeted Allocation of KV cache for Long-context Inference
Ahmed Burak Gulhan, Krishna Teja Chitty-Venkata, Murali Emani +2
In Large Language Model (LLM) inference, Key-Value (KV) caches (KV-caches) are essential for reducing time complexity. However, they result in a linear increase in GPU memory as th…