相关论文: Towards Observation Lakehouses: Living, Interactiv…
Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…
Data lakehouses (LHs) are at the core of current cloud analytics stacks by providing elastic, relational compute on data in cloud data lakes across vendors. For relational semantics, they rely on open table formats (OTFs). Unfortunately,…
Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent decisions across cohort construction, analysis, and reporting. Prior evaluations of LLM…
When successful, Open Source Software (OSS) projects create enormous value, but most never reach a sustainable state. Recent work has produced accurate models that forecast OSS sustainability, yet these models rarely tell maintainers what…
Traditional data lakes provide critical data infrastructure for analytical workloads by enabling time travel, running SQL queries, ingesting data with ACID transactions, and visualizing petabyte-scale datasets on cloud storage. They allow…
Inductive reasoning, a cornerstone of human cognition, enables generalization from limited data but hasn't yet been fully achieved by large language models (LLMs). While modern LLMs excel at reasoning tasks, their ability to maintain stable…
Lakehouses are now the default substrate for analytics and AI, but they remain fragile under concurrent, untrusted change: schema mismatches often surface only at runtime, development and production easily diverge, and multi-table pipelines…
We present an interactive framework for evaluating whether large language models (LLMs) exhibit genuine "understanding" in a simple yet strategic environment. As a running example, we focus on Rock-Paper-Scissors (RPS), which, despite its…
Codebooks -- documents that operationalize concepts and outline annotation procedures -- are used almost universally by social scientists when coding political texts. To code these texts automatically, researchers are increasing turning to…
LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership, and unauthorized reuse difficult to establish from observed…
The advent of language models (LMs) has the potential to dramatically accelerate tasks that may be cast to text-processing; however, real-world adoption is hindered by concerns regarding safety, explainability, and bias. How can we…
Reservoir computing (RC), is a class of computational methods such as Echo State Networks (ESN) and Liquid State Machines (LSM) describe a generic method to perform pattern recognition and temporal analysis with any non-linear system. This…
Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid State Machine (LSM) is a bio-inspired RC model that mimics the cortical microcircuits and uses spiking neural networks…
Human Activity Recognition is a time-series analysis problem. A popular analysis procedure used by the community assumes an optimal window length to design recognition pipelines. However, in the scenario of smart homes, where activities are…
Large Language Models (LLMs) are emerging as promising tools for automated reinforcement learning (RL) reward design, owing to their robust capabilities in commonsense reasoning and code generation. By engaging in dialogues with RL agents,…
In light of the rapid adoption of AI coding assistants, LLM-assisted development has become increasingly prevalent, creating an urgent need for robust evaluation of generated code quality. Existing benchmarks often require extensive manual…
Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…
Regional rainfall-runoff modeling is an old but still mostly out-standing problem in Hydrological Sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple…
A wealth of operational intelligence is locked within the unstructured free-text of wind turbine maintenance logs, a resource largely inaccessible to traditional quantitative reliability analysis. While machine learning has been applied to…
The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…