4988 papers
This paper establishes that confidence-based abstention in ranked decision systems improves quality only under specific structural conditions, demonstrating that while structural uncertainty allows for monotonic gains, contextual uncertainty fundamentally undermines standard confidence signals and exception-based interventions, necessitating domain-specific diagnostic checks before deployment.
This paper introduces the Overfitting-Underfitting Indicator (OUI) as an efficient, early-stage metric based on hidden neuron activation patterns to distinguish optimal learning rates in PPO actor-critic training, demonstrating its superior ability to prune unpromising runs compared to traditional criteria by revealing distinct structural signatures in actor and critic networks.
This paper introduces "neural debuggers," a new class of language models that emulate traditional debugging interactions like setting breakpoints and stepping through code to enable both forward and inverse execution prediction, thereby laying the foundation for more powerful agentic coding systems and automated debugging.
This paper demonstrates that reasoning consistently enhances honesty in large language models by guiding them through a representational space where deceptive states are metastable and easily disrupted, ultimately nudging the models toward more stable, honest defaults.
This paper introduces BEACON, a language-conditioned navigation system that overcomes the limitations of existing 2D image-space methods by predicting an occlusion-aware Bird's-Eye View affordance heatmap from surround-view RGB-D observations, thereby significantly improving the accuracy of inferring traversable targets in occluded regions.
This paper extends the classical "bee equation" for swarm decision-making into an agent-based model where emotional valence and arousal modulate interaction rates, revealing how emotional contagion and non-linear amplification mechanisms bias consensus outcomes and accelerate convergence in collective choices.
This paper presents a study of a large language model-powered "sighted guide" for blind and low vision users in social virtual reality, revealing that participants adapt their interaction from a tool-based approach when alone to a companionable relationship in the presence of others, thereby offering key design recommendations for future accessible VR guides.
This paper challenges the standard view of superposition in neural networks by demonstrating that, unlike in idealized uncorrelated settings where interference is merely noise, realistic feature correlations allow models to arrange features so that interference becomes constructive, thereby naturally forming the semantic clusters and cyclical structures observed in real language models.
This paper introduces two online neural network-based algorithms for change-point detection in large time series that demonstrate linear computational complexity, outperform existing methods on various datasets, and are proven to converge to optimal solutions under specific conditions.
This paper provides a comprehensive overview of Automated Reinforcement Learning (AutoRL), surveying existing literature including recent LLM-based techniques, discussing promising non-tailored methods for future integration, and outlining current challenges and research directions in automating MDP modeling, algorithm selection, and hyper-parameter optimization.
This paper proposes an uncertainty-aware, explainable-by-design subsequence-based model that achieves state-of-the-art classification performance for astronomical uncertain time series by incorporating data uncertainty as an input, thereby enabling domain experts to inspect predictions and potentially inspire new theoretical astrophysics developments.
This survey reviews the recent advances in Large Language Models (LLMs) by covering their background, key findings, and mainstream techniques across four major aspects: pre-training, adaptation tuning, utilization, and capacity evaluation, while also summarizing available resources and discussing future challenges.
This survey reviews the application of utility theory to cognitive modeling in robotics, tracing its evolution from behavior-based approaches to value systems that guide decision-making, learning, and cooperation in single and multi-agent environments, while identifying current limitations and proposing future research directions.
This paper proposes and validates a loop-based algorithm for the online, conflict-free scheduling and routing of automated guided vehicles in pickup and delivery systems, demonstrating its superior or comparable performance to exact, greedy, and metaheuristic methods in terms of solution quality and computational efficiency.
This paper introduces Agent-OM, a novel framework leveraging Siamese LLM agents and specialized tools to address ontology matching challenges, demonstrating competitive performance on simple tasks and significant improvements on complex and few-shot scenarios compared to state-of-the-art systems.
This paper presents a machine learning-focused survey of Computerized Adaptive Testing (CAT), exploring how ML techniques can optimize measurement models, question selection, bank construction, and test control to create more robust, fair, and efficient adaptive assessment systems across various domains.
This paper introduces Fast Explanation (FEX), a novel framework that utilizes policy gradient optimization to represent attribution-based explanations as probability distributions, achieving over 97% reduction in inference time and 70% less memory usage compared to traditional model-agnostic methods while maintaining high-quality, scalable explanations for image and text classification tasks.
This paper identifies a "corruption stage" in few-shot fine-tuned diffusion models caused by a narrowed learning distribution and proposes a Bayesian Neural Network approach with variational inference to broaden this distribution, thereby mitigating corruption and improving image fidelity, quality, and diversity without additional inference costs.
LAMBDA is a novel, open-source, code-free multi-agent system that leverages large language models with collaborative programmer and inspector roles, along with a knowledge integration mechanism and user intervention capabilities, to enhance the accessibility and efficiency of data analysis for diverse users.
The paper proposes OTAD, a novel two-step defense framework that combines optimal transport theory with convex integration to train deep neural networks that achieve both high accuracy and certified local Lipschitz robustness against adversarial attacks.