Related papers: SeLeP: Learning Based Semantic Prefetching for Exp…
The growth of the World Wide Web has emphasized the need for improvement in user latency. One of the techniques that are used for improving user latency is Caching and another is Web Prefetching. Approaches that bank solely on caching offer…
Prefetching web pages is a well-studied solution to reduce network latency by predicting users' future actions based on their past behaviors. However, such techniques are largely unexplored on mobile platforms. Today's privacy regulations…
Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior…
Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…
The use of semantic features can improve the efficiency of target search in unknown environments for robotic search and rescue missions. Current target search methods rely on training with large datasets of similar domains, which limits the…
Large Language Models (LLMs) have revolutionized numerous domains, driving the rise of Language-Model-as-a-Service (LMaaS) platforms that process millions of queries daily. These platforms must minimize latency and meet Service Level…
Modern memory hierarchies work well with applications that have good spatial locality. Evolving (dynamic) graphs are important applications widely used to model graphs and networks with edge and vertex changes. They exhibit irregular memory…
Semantic search, a process aimed at delivering highly relevant search results by comprehending the searcher's intent and the contextual meaning of terms within a searchable dataspace, plays a pivotal role in information retrieval. In this…
Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present…
Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…
Memory disaggregation over RDMA can improve the performance of memory-constrained applications by replacing disk swapping with remote memory accesses. However, state-of-the-art memory disaggregation solutions still use data path components…
Real-time log analysis is the cornerstone of observability for modern infrastructure. However, existing online parsers are architecturally unsuited for the dynamism of production environments. Built on fundamentally static template models,…
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…
Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence…
Recent advancements in large language models (LLMs) have significantly improved performance on the Text-to-SQL task. However, prior approaches typically rely on static, pre-processed database information provided at inference time, which…
Database systems often rely on historical query traces to perform workload-based performance tuning. However, real production workloads are time-evolving, making historical queries ineffective for optimizing future workloads. To address…
Database query performance problem determination is often performed by analyzing query execution plans (QEPs) in addition to other performance data. As the query workloads that organizations run, have become larger and more complex,…
Continual Semantic Parsing (CSP) aims to train parsers to convert natural language questions into SQL across tasks with limited annotated examples, adapting to the real-world scenario of dynamically updated databases. Previous studies…
With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance. However, many times these models systematically fail on tail data or rare groups not…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…