arXiv:2602.00943v1 Announce Type: new Abstract: Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thompson Sampling (TS) is often initialized with a uniform Beta(1,1) prior, implicitly assuming a 50% success rate for unseen items. When true base rates are far lower, this optimistic prior systematically over-allocates to weak items. The impact is amplified by batched policy updates and […]

Ver mais

arXiv:2602.04003v1 Announce Type: new Abstract: Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce […]

Ver mais

On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy and policy updates must be conservative. In this paper, we revisit policy representation as a first-class design choice for on-policy optimization. We study discretized categorical actors that represent each action dimension with a distribution over bins, yielding a policy objective that resembles a cross-entropy loss. Building […]

Ver mais

arXiv:2601.15291v1 Announce Type: new Abstract: Independent navigation is a core aspect of maintaining social participation and individual health for vulnerable populations. While historic cities such as Edinburgh, as the capital of Scotland, often feature well-established public transport systems, urban accessibility challenges remain and are exacerbated by a complex landscape, especially for groups with multiple vulnerabilities such as the blind elderly. With limited research examining how real-time data feeds and developments in artificial intelligence can enhance navigation aids, we […]

Ver mais

Professor Naftali Tishby passed away in 2021. Hope the post can introduce his cool idea of information bottleneck to more people. Recently I watched the talk “Information Theory in Deep Learning” by Prof Naftali Tishby and found it very interesting. He presented how to apply the information theory to study the growth and transformation of deep neural networks during training. Using the Information Bottleneck (IB) method, he proposed a new learning bound for deep neural networks (DNN), as […]

Ver mais

arXiv:2602.05052v1 Announce Type: new Abstract: We present a unified algorithmic framework for the numerical solution, constrained optimization, and physics-informed learning of PDEs with a variational structure. Our framework is based on a Galerkin discretization of the underlying variational forms, and its high efficiency stems from a novel highly-optimized and GPU-compliant TensorGalerkin framework for linear system assembly (stiffness matrices and load vectors). TensorGalerkin operates by tensorizing element-wise operations within a Python-level Map stage and then performs global reduction with […]

Ver mais

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to distribution shift and inherent conflicts between style and reward. Existing methods, despite introducing numerous definitions of style, often fail to reconcile these objectives effectively. To address these challenges, we propose a unified definition of behavior style and instantiate it into a practical framework. Building on this, we introduce […]

Ver mais

arXiv:2601.16398v1 Announce Type: new Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior only through input-output testing. These methods are limited to tests constructed in the input space, often generated by heuristics. In addition, many socially relevant model properties (e.g., gender bias) are abstract and difficult to measure through text-based inputs alone. To […]

Ver mais

arXiv:2602.07142v1 Announce Type: new Abstract: Collaboration is a cornerstone of 21st-century learning, yet teachers continue to face challenges in supporting productive peer interaction. Emerging generative AI tools offer new possibilities for scaffolding collaboration, but their role in mediating in-person group work remains underexplored, especially from the perspective of educators. This paper presents findings from an exploratory qualitative study with 33 K12 teachers who interacted with Phoenix, a voice-based conversational agent designed to function as a near-peer in face-to-face […]

Ver mais