Joy Arulraj

Pramod Chunduri, Francisco Romero, Ali Payani et al.

Long-context question answering (QA) over lengthy documents is critical for applications such as financial analysis, legal review, and scientific research. Current approaches, such as processing entire documents via a single LLM call or retrieving relevant chunks via RAG have two drawbacks: First, as context size increases, response quality can degrade, impacting accuracy. Second, iteratively processing hundreds of input documents can incur prohibitively high costs in API calls. To improve response quality and reduce the number of iterations needed to get the desired response, users tend to add domain knowledge to their prompts. However, existing systems fail to systematically capture and use this knowledge to guide query processing. Domain knowledge is treated as prompt tokens alongside the document: the LLM may or may not follow it, there is no reduction in computational cost, and when outputs are incorrect, users must manually iterate. We present Halo, a long-context QA framework that automatically extracts domain knowledge from user prompts and applies it as executable operators across a multi-stage query execution pipeline. Halo identifies three common forms of domain knowledge - where in the document to look, what content to ignore, and how to verify the answer - and applies each at the pipeline stage where it is most effective: pruning the document before chunk selection, filtering irrelevant chunks before inference, and ranking candidate responses after generation. To handle imprecise or invalid domain knowledge, Halo includes a fallback mechanism that detects low-quality operators at runtime and selectively disables them. Our evaluation across finance, literature, and scientific datasets shows that Halo achieves up to 13% higher accuracy and 4.8x lower cost compared to baselines, and enables a lightweight open-source model to approach frontier LLM accuracy at 78x lower cost.

Gaurav Tarlok Kakkar, Jiashen Cao, Aubhro Sengupta et al.

Query optimization in relational database management systems (DBMSs) is critical for fast query processing. The query optimizer relies on precise selectivity and cost estimates to effectively optimize queries prior to execution. While this strategy is effective for relational DBMSs, it is not sufficient for DBMSs tailored for processing machine learning (ML) queries. In ML-centric DBMSs, query optimization is challenging for two reasons. First, the performance bottleneck of the queries shifts to user-defined functions (UDFs) that often wrap around deep learning models, making it difficult to accurately estimate UDF statistics without profiling the query. This leads to inaccurate statistics and sub-optimal query plans. Second, the optimal query plan for ML queries is data-dependent, necessitating DBMSs to adapt the query plan on the fly during execution. So, a static query plan is not sufficient for such queries. In this paper, we present Hydro, an ML-centric DBMS that utilizes adaptive query processing (AQP) for efficiently processing ML queries. Hydro is designed to quickly evaluate UDF-based query predicates by ensuring optimal predicate evaluation order and improving the scalability of UDF execution. By integrating AQP, Hydro continuously monitors UDF statistics, routes data to predicates in an optimal order, and dynamically allocates resources for evaluating predicates. We demonstrate Hydro's efficacy through four illustrative use cases, delivering up to 11.52x speedup over a baseline system.

Pramod Chunduri, Yao Lu, Joy Arulraj

Efficiently re-identifying and tracking objects across a network of cameras is crucial for applications like traffic surveillance. Spatula is the state-of-the-art video database management system (VDBMS) for processing Re-ID queries. However, it suffers from two limitations. Its spatio-temporal filtering scheme has limited accuracy on large camera networks due to localized camera history. It is not suitable for critical video analytics applications that require high recall due to a lack of support for adaptive query processing. In this paper, we present Tracer, a novel VDBMS for efficiently processing Re-ID queries using an adaptive query processing framework. Tracer selects the optimal camera to process at each time step by training a recurrent network to model long-term historical correlations. To accelerate queries under a high recall constraint, Tracer incorporates a probabilistic adaptive search model that processes camera feeds in incremental search windows and dynamically updates the sampling probabilities using an exploration-exploitation strategy. To address the paucity of benchmarks for the Re-ID task due to privacy concerns, we present a novel synthetic benchmark for generating multi-camera Re-ID datasets based on real-world traffic distribution. Our evaluation shows that Tracer outperforms the state-of-the-art cross-camera analytics system by 3.9x on average across diverse datasets.

Xinyu Liu, Qi Zhou, Joy Arulraj et al.

Because database systems are the critical component of modern data-intensive applications, it is important to ensure that they operate correctly. To this end, developers extensively test these systems to eliminate bugs that negatively affect functionality. In addition to functional bugs, however, there is another important class of bugs: performance bugs. These bugs negatively affect the response time of a database system and can therefore affect the overall performance of the system. Despite their impact on end-user experience, performance bugs have received considerably less attention than functional bugs. In this paper, we present AMOEBA, a system for automatically detecting performance bugs in database systems. The core idea behind AMOEBA is to construct query pairs that are semantically equivalent to each other and then compare their response time on the same database system. If the queries exhibit a significant difference in their runtime performance, then the root cause is likely a performance bug in the system. We propose a novel set of structure and predicate mutation rules for constructing query pairs that are likely to uncover performance bugs. We introduce feedback mechanisms for improving the efficacy and computational efficiency of the tool. We evaluate AMOEBA on two widely-used DBMSs, namely PostgreSQL and CockroachDB. AMOEBA has discovered 20 previously-unknown performance bugs, among which developers have already confirmed 14 and fixed 4.

Pramod Chunduri, Jaeho Bang, Yao Lu et al.

Detection and localization of actions in videos is an important problem in practice. State-of-the-art video analytics systems are unable to efficiently and effectively answer such action queries because actions often involve a complex interaction between objects and are spread across a sequence of frames; detecting and localizing them requires computationally expensive deep neural networks. It is also important to consider the entire sequence of frames to answer the query effectively. In this paper, we present ZEUS, a video analytics system tailored for answering action queries. We present a novel technique for efficiently answering these queries using deep reinforcement learning. ZEUS trains a reinforcement learning agent that learns to adaptively modify the input video segments that are subsequently sent to an action classification network. The agent alters the input segments along three dimensions - sampling rate, segment length, and resolution. To meet the user-specified accuracy target, ZEUS's query optimizer trains the agent based on an accuracy-aware, aggregate reward function. Evaluation on three diverse video datasets shows that ZEUS outperforms state-of-the-art frame- and window-based filtering techniques by up to 22.1x and 4.7x, respectively. It also consistently meets the user-specified accuracy target across all queries.

Abhijit Suprem, Joy Arulraj, Calton Pu et al.

Recent advances in computer vision have led to a resurgence of interest in visual data analytics. Researchers are developing systems for effectively and efficiently analyzing visual data at scale. A significant challenge that these systems encounter lies in the drift in real-world visual data. For instance, a model for self-driving vehicles that is not trained on images containing snow does not work well when it encounters them in practice. This drift phenomenon limits the accuracy of models employed for visual data analytics. In this paper, we present a visual data analytics system, called ODIN, that automatically detects and recovers from drift. ODIN uses adversarial autoencoders to learn the distribution of high-dimensional images. We present an unsupervised algorithm for detecting drift by comparing the distributions of the given data against that of previously seen data. When ODIN detects drift, it invokes a drift recovery algorithm to deploy specialized models tailored towards the novel data points. These specialized models outperform their non-specialized counterpart on accuracy, performance, and memory footprint. Lastly, we present a model selection algorithm for picking an ensemble of best-fit specialized models to process a given input. We evaluate the efficacy and efficiency of ODIN on high-resolution dashboard camera videos captured under diverse environments from the Berkeley DeepDrive dataset. We demonstrate that ODIN's models deliver 6x higher throughput, 2x higher accuracy, and 6x smaller memory footprint compared to a baseline system without automated drift detection and recovery.