Related papers: CAPE: Capability Achievement via Policy Execution
Companies have considered adoption of various high-level artificial intelligence (AI) principles for responsible AI, but there is less clarity on how to implement these principles as organizational practices. This paper reviews the…
Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing methods often struggle due to catastrophic forgetting,…
Sequential recommendation (SR), which encodes user activity to predict the next action, has emerged as a widely adopted strategy in developing commercial personalized recommendation systems. A critical component of modern SR models is the…
Both student retention in higher education and artificial intelligence governance face a common structural challenge: the application of linear regulatory frameworks to complex adaptive systems. Risk-based approaches dominate both domains,…
The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizing these inputs. Current CE methods rely on manually crafted…
Evaluations of generative models are now ubiquitous, and their outcomes critically shape public and scientific expectations of AI's capabilities. Yet skepticism about their reliability continues to grow. How can we know that a reported…
Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions…
Generative models often use human evaluations to measure the perceived quality of their outputs. Automated metrics are noisy indirect proxies, because they rely on heuristics or pretrained embeddings. However, up until now, direct human…
Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments, benchmarks stabilize the dominant paradigm by narrowing what counts as progress. Over…
This paper reports a case study on how explainability requirements were elicited during the development of an AI system for predicting cerebral palsy (CP) risk in infants. Over 18 months, we followed a development team and hospital…
Authorship Verification (AV) (do two documents have the same author?) is essential in many real-life applications. AV is often used in privacy-sensitive domains that require an offline proprietary model that is deployed on premises, making…
In practical applications, machine learning algorithms are often needed to learn classifiers that optimize domain specific performance measures. Previously, the research has focused on learning the needed classifier in isolation, yet…
Unsupervised Environment Design (UED) offers a promising paradigm for improving reinforcement learning generalization by adaptively shaping training environments, but it requires reliable environment evaluation to remain effective. However,…
Treatment non-compliance, where individuals deviate from their assigned experimental conditions, frequently complicates the estimation of causal effects. To address this, we introduce a novel learning framework based on a mixture of experts…
As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…
Robotic assistance in scientific laboratories requires procedurally correct long-horizon manipulation, reliable execution under limited supervision, and robustness in low-demonstration regimes. Such conditions greatly challenge end-to-end…
Model Predictive Control (MPC) is widely used to achieve performance objectives, while enforcing operational and safety constraints. Despite its high performance, MPC often demands significant computational resources, making it challenging…
The efficiency of an AI system is contingent upon its ability to align with the specified requirements of a given task. How-ever, the inherent complexity of tasks often introduces the potential for harmful implications or adverse actions.…
The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…
Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution environments. As MCP-based systems scale to incorporate larger tool catalogs and multiple…