arXiv subjects

Chetan Sharma

Publications and source records attributed to Chetan Sharma.

4 recordsLinked to original sources

arXiv2026

Workload-Aware Caching for Multi-Agent Systems

Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries. However, existing cache eviction policies treat all cached entries uniformly based on access history, ignoring structural and workload signals uniquely available in agentic execution environments. We present a workload-aware eviction policy that combines three signals, namely recomputation cost, DAG dependency count, and agent invocation frequency, into a unified scoring function that retains the most valuable entries under memory constraints. Evaluated across three multi-agent benchmarks spanning diverse reuse regimes, our policy reduces latency by up to 64.7% relative to the uncached baseline and achieves on average a 31.1% latency reduction over the next best finite-capacity baseline, while approaching the performance of an unbounded cache and maintaining accuracy on par with or exceeding all competing finite-capacity methods. We further show that workload-aware content caching is complementary to other agentic system optimization methods, including plan-level caching and parallel agent execution, with each technique targeting a distinct efficiency bottleneck in multi-agent pipelines.

cs.AI↗

arXiv2025

Role of the Pretraining and the Adaptation data sizes for low-resource real-time MRI video segmentation

Real-time Magnetic Resonance Imaging (rtMRI) is frequently used in speech production studies as it provides a complete view of the vocal tract during articulation. This study investigates the effectiveness of rtMRI in analyzing vocal tract movements by employing the SegNet and UNet models for Air-Tissue Boundary (ATB)segmentation tasks. We conducted pretraining of a few base models using increasing numbers of subjects and videos, to assess performance on two datasets. First, consisting of unseen subjects with unseen videos from the same data source, achieving 0.33% and 0.91% (Pixel-wise Classification Accuracy (PCA) and Dice Coefficient respectively) better than its matched condition. Second, comprising unseen videos from a new data source, where we obtained an accuracy of 99.63% and 98.09% (PCA and Dice Coefficient respectively) of its matched condition performance. Here, matched condition performance refers to the performance of a model trained only on the test subjects which was set as a benchmark for the other models. Our findings highlight the significance of fine-tuning and adapting models with limited data. Notably, we demonstrated that effective model adaptation can be achieved with as few as 15 rtMRI frames from any new dataset.

eess.AS↗

arXiv2021

LEGOStore: A Linearizable Geo-Distributed Store Combining Replication and Erasure Coding

We design and implement LEGOStore, an erasure coding (EC) based linearizable data store over geo-distributed public cloud data centers (DCs). For such a data store, the confluence of the following factors opens up opportunities for EC to be latency-competitive with replication: (a) the necessity of communicating with remote DCs to tolerate entire DC failures and implement linearizability; and (b) the emergence of DCs near most large population centers. LEGOStore employs an optimization framework that, for a given object, carefully chooses among replication and EC, as well as among various DC placements to minimize overall costs. To handle workload dynamism, LEGOStore employs a novel agile reconfiguration protocol. Our evaluation using a LEGOStore prototype spanning 9 Google Cloud Platform DCs demonstrates the efficacy of our ideas. We observe cost savings ranging from moderate (5-20\%) to significant (60\%) over baselines representing the state of the art while meeting tail latency SLOs. Our reconfiguration protocol is able to transition key placements in 3 to 4 inter-DC RTTs ($<$ 1s in our experiments), allowing for agile adaptation to dynamic conditions.

cs.DC↗

arXiv2021

Generational Frameshifts in Technology: Computer Science and Neurosurgery, The VR Use Case

We are at a unique moment in history where there is a confluence of technologies which will synergistically come together to transform the practice of neurosurgery. These technological transformations will be all-encompassing, including improved tools and methods for intraoperative performance of neurosurgery, scalable solutions for asynchronous neurosurgical training and simulation, as well as broad aggregation of operative data allowing fundamental changes in quality assessment, billing, outcome measures, and dissemination of surgical best practices. The ability to perform surgery more safely and more efficiently while capturing the operative details and parsing each component of the operation will open an entirely new epoch advancing our field and all surgical specialties. The digitization of all components within the operating room will allow us to leverage the various fields within computer and computational science to obtain new insights that will improve care and delivery of the highest quality neurosurgery regardless of location. The democratization of neurosurgery is at hand and will be driven by our development, extraction, and adoption of these tools of the modern world. Virtual reality provides a good example of how consumer-facing technologies are finding a clear role in industry and medicine and serves as a notable example of the confluence of various computer science technologies creating a novel paradigm for scaling human ability and interactions. The authors describe the technology ecosystem that has come and highlight a myriad of computational and data sciences that will be necessary to enable the operating room of the near future.

cs.HC↗