11 citations · 24 across the 26 of their papers we have counts for
28 papers
Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents
Ritul Satish, Prasoon Sinha, Akiho Kawada +1
As LLM agents tackle longer tasks, they increasingly compress growing histories of reasoning, actions, and tool outputs. Compression can reduce token use, but it also changes the i…
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
Dan Jacobellis, Neeraja J. Yadwadkar
In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources p…
FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder
Dan Jacobellis, Neeraja J. Yadwadkar
Media compression standards have reached a plateau in terms of the rate-distortion-complexity trade-off, limiting the ability to offload expensive AI perception to the cloud in app…
LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation
Dan Jacobellis, Neeraja J. Yadwadkar
Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized c…
SPEC CPU2026: Characterization, Representativeness, and Cross-Suite Comparison
Ruihao Li, Andrew Jacob, Neeraja J. Yadwadkar +1
Specialized accelerators dominate AI workloads, but CPUs remain critical for latency-sensitive workloads, agentic AI, and many other everyday services. Their performance therefore…
LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9
Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on…
Old is Gold: Optimizing Single-threaded Applications with Exgen-Malloc
Ruihao Li, Lizy K. John, Neeraja J. Yadwadkar
Memory allocators hide beneath nearly every application stack, yet their performance footprint extends far beyond their code size. Even small inefficiencies in the allocators rippl…
DeDelayed: Deleting Remote Inference Delay via On-Device Correction
Dan Jacobellis, Mateen Ulhaq, Fabien Racapé +2
Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet,…
Composer: A Search Framework for Hybrid Neural Architecture Design
Bilge Acun, Prasoon Sinha, Newsha Ardalani +7
Hybrid model architectures that combine computational primitives (e.g., Attention, MLP) in different ratios have shown promising performance beyond Transformers. Some studies have…
SpeedMalloc: Improving Multi-threaded Applications via a Lightweight Core for Memory Allocation
Ruihao Li, Qinzhe Wu, Krishna Kavi +4
Memory allocation, though constituting only a small portion of the executed code, can have a "butterfly effect" on overall program performance, leading to significant and far-reach…
Oneiros: KV Cache Optimization through Parameter Remapping for Multi-tenant LLM Serving
Ruihao Li, Shagnik Pal, Vineeth Narayan Pullu +4
KV cache accelerates LLM inference by avoiding redundant computation, at the expense of memory. To support larger KV caches, prior work extends GPU memory with CPU memory via CPU-o…
Simulating Rumor Spreading in Social Networks using LLM Agents
Tianrui Hu, Dimitrios Liakopoulos, Xiwen Wei +2
With the rise of social media, misinformation has become increasingly prevalent, fueled largely by the spread of rumors. This study explores the use of Large Language Model (LLM) a…
iServe: An Intent-based Serving System for LLMs
Dimitrios Liakopoulos, Tianrui Hu, Prasoon Sinha +1
Large Language Models (LLMs) are becoming ubiquitous across industries, where applications demand they fulfill diverse user intents. However, developers currently face the challeng…
Learned Compression for Compressed Learning
Dan Jacobellis, Neeraja J. Yadwadkar
Modern sensors produce increasingly rich streams of high-resolution data. Due to resource constraints, machine learning systems discard the vast majority of this information via re…
SoK: A Systems Perspective on Compound AI Threats and Countermeasures
Sarbartha Banerjee, Prateek Sahu, Mulong Luo +3
Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior res…
Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference
Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9
Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing com…
Shabari: Delayed Decision-Making for Faster and Efficient Serverless Functions
Prasoon Sinha, Kostis Kaffes, Neeraja J. Yadwadkar
Serverless computing relieves developers from the burden of resource management, thus providing ease-of-use to the users and the opportunity to optimize resource utilization for th…
Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models
Dan Jacobellis, Daniel Cummings, Neeraja J. Yadwadkar
In the field of neural data compression, the prevailing focus has been on optimizing algorithms for either classical distortion metrics, such as PSNR or SSIM, or human perceptual q…
MOSEL: Inference Serving Using Dynamic Modality Selection
Bodun Hu, Le Xu, Jeongyoon Moon +2
Rapid advancements over the years have helped machine learning models reach previously hard-to-achieve goals, sometimes even exceeding human capabilities. However, to attain the de…
Dirigo: Self-scaling Stateful Actors For Serverless Real-time Data Processing
Le Xu, Divyanshu Saxena, Neeraja J. Yadwadkar +2
We propose Dirigo, a distributed stream processing service built atop virtual actors. Dirigo achieves both a high level of resource efficiency and performance isolation driven by u…
Lightweight ML-based Runtime Prefetcher Selection on Many-core Platforms
Erika S. Alcorta, Mahesh Madhav, Scott Tetrick +2
Modern computer designs support composite prefetching, where multiple individual prefetcher components are used to target different memory access patterns. However, multiple prefet…
Sidecars on the Central Lane: Impact of Network Proxies on Microservices
Prateek Sahu, Lucy Zheng, Marco Bueso +3
Cloud applications are moving away from monolithic model towards loosely-coupled microservices designs. Service meshes are widely used for implementing microservices applications m…
SOL: Safe On-Node Learning in Cloud Platforms
Yawen Wang, Daniel Crankshaw, Neeraja J. Yadwadkar +3
Cloud platforms run many software agents on each server node. These agents manage all aspects of node operation, and in some cases frequently collect data and make decisions. Unfor…
Practical Scheduling for Real-World Serverless Computing
Kostis Kaffes, Neeraja J. Yadwadkar, Christos Kozyrakis
Serverless computing has seen rapid growth due to the ease-of-use and cost-efficiency it provides. However, function scheduling, a critical component of serverless systems, has bee…