33 citations · 85 across the 18 of their papers we have counts for
18 papers
Action Chunk Scheduling for Batched Robot Policy Serving
Rohan Bansal, David He, Nadun Ranawaka Arachchige +4
Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (VLA) and other foundation mo…
Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)
Rajveer Bachkaniwala, Chengqi Luo, Richard So +2
Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first…
Halo: Domain-Aware Query Optimization for Long-Context Question Answering
Pramod Chunduri, Francisco Romero, Ali Payani +2
Long-context question answering (QA) over lengthy documents is critical for applications such as financial analysis, legal review, and scientific research. Current approaches, such…
ActionEngine: From Reactive to Programmatic Web Agents via State Machine Memory
Hongbin Zhong, Fazle Faisal, Luis França +4
Many web agents operate through a reactive execution loop: they observe the current interface, reason about the next action, execute it, and repeat. This design incurs latency and…
HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning[Technical Report]
Hongbin Zhong, Matthew Lentz, Nina Narodytska +2
Enterprise deployments of vector databases require access control policies to protect sensitive data. These systems often implement access control through hybrid vector queries tha…
A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems
Lew Lefton, Kexin Rong, Chinar Dankhara +3
In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities.…
SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
Renzhi Wu, Pramod Chunduri, Dristi J Shah +5
In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows us…
Dynamic Data Layout Optimization with Worst-case Guarantees
Kexin Rong, Paul Liu, Sarah Ashok Sonje +1
Many data analytics systems store and process large datasets in partitions containing millions of rows. By mapping rows to partitions in an optimized way, it is possible to improve…
Falcon: Fair Active Learning using Multi-armed Bandits
Ki Hyun Tae, Hantian Zhang, Jaeyoung Park +2
Biased data can lead to unfair machine learning models, highlighting the importance of embedding fairness at the beginning of data analysis, particularly during dataset curation an…
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
Yao Lu, Song Bian, Lequn Chen +19
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in t…
DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data
Peng Li, Zhiyi Chen, Xu Chu +1
Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time…
Rethinking Similarity Search: Embracing Smarter Mechanisms over Smarter Data
Renzhi Wu, Jingfan Meng, Jie Jeff Xu +2
In this vision paper, we propose a shift in perspective for improving the effectiveness of similarity search. Rather than focusing solely on enhancing the data quality, particularl…
Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization
Amey Agrawal, Sameer Reddy, Satwik Bhattamishra +4
With the increase in the scale of Deep Learning (DL) training workloads in terms of compute resources and time consumption, the likelihood of encountering in-training failures rise…
Approximate Partition Selection for Big-Data Workloads using Summary Statistics
Kexin Rong, Yao Lu, Peter Bailis +2
Many big-data clusters store data in large partitions that support access at a coarse, partition-level granularity. As a result, approximate query processing via row-level sampling…
CrossTrainer: Practical Domain Adaptation with Loss Reweighting
Justin Chen, Edward Gan, Kexin Rong +2
Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful w…
Locality-Sensitive Hashing for Earthquake Detection: A Case Study of Scaling Data-Driven Science
Kexin Rong, Clara E. Yoon, Karianne J. Bergen +4
In this work, we report on a novel application of Locality Sensitive Hashing (LSH) to seismic data at scale. Based on the high waveform similarity between reoccurring earthquakes,…
ASAP: Prioritizing Attention via Time Series Smoothing
Kexin Rong, Peter Bailis
Time series visualization of streaming telemetry (i.e., charting of key metrics such as server load over time) is increasingly prevalent in modern data platforms and applications.…
MacroBase: Prioritizing Attention in Fast Data
Peter Bailis, Edward Gan, Samuel Madden +3
As data volumes continue to rise, manual inspection is becoming increasingly untenable. In response, we present MacroBase, a data analytics engine that prioritizes end-user attenti…