Related papers: Implementing Performance Competitive Logical Recov…
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…
We address policy learning with logged data in contextual bandits. Current offline-policy learning algorithms are mostly based on inverse propensity score (IPS) weighting requiring the logging policy to have \emph{full support} i.e. a…
Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately…
Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow…
Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code generation, numerical reasoning, and dialog. Existing work…
Domain-specific systems-on-chip, a class of heterogeneous many-core systems, are recognized as a key approach to narrow down the performance and energy-efficiency gap between custom hardware accelerators and programmable processors.…
In this paper, we try to focus the reader's interest on the problems that transactional systems have to resolve for taking advantage of commutativity in a serializable and recoverable way. Our framework is, (as others), based on the use of…
Media failures usually leave database systems unavailable for several hours until recovery is complete, especially in applications with large devices and high transaction volume. Previous work introduced a technique called single-pass…
When attempting to recover functions from observational data, one naturally seeks to do so in an optimal manner with respect to some modeling assumption. With a focus put on the worst-case setting, this is the standard goal of Optimal…
AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a…
Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundamentally misaligned. Current RAG systems…
Given its high integration density, high speed, byte addressability, and low standby power, non-volatile or persistent memory is expected to supplement/replace DRAM as main memory. Through persistency programming models (which define…
With the blossom of large language models (LLMs), inference efficiency becomes increasingly important. Various approximation methods are proposed to reduce the cost at inference time. Contextual Sparsity (CS) is appealing for its…
A mobile computing system is a distributed system in which at least one of the processes is mobile. They are constrained by lack of stable storage, low network bandwidth, mobility, frequent disconnection and limited battery life.…
Performance debugging in production is a fundamental activity in modern service-based systems. The diagnosis of performance issues is often time-consuming, since it requires thorough inspection of large volumes of traces and performance…
Aggregation has been an important operation since the early days of relational databases. Today's Big Data applications bring further challenges when processing aggregation queries, demanding adaptive aggregation algorithms that can process…
Analytical database systems are typically designed to use a column-first data layout to access only the desired fields. On the other hand, storing data row-first works great for accessing, inserting, or updating entire rows. Transforming…
Tabled evaluation is an implementation technique that solves some problems of traditional Prolog systems in dealing with recursion and redundant computations. Most tabling engines determine if a tabled subgoal will produce or consume…
The rapid adoption of AI-powered applications demands high-performance, scalable, and efficient cloud database solutions, as traditional architectures often struggle with AI-driven workloads requiring real-time data access, vector search,…
Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC). A popular approach to improve the system's performance is to improve the…