arXiv:2602.12342v1 Announce Type: new Abstract: How can we train agents to navigate uncertainty over long horizons? In this work, we propose {Delta}Belief-RL, which leverages a language model’s own intrinsic beliefs to reward intermediate progress. Our method utilizes the change in the probability an agent assigns to the target solution for credit assignment. By training on synthetic interaction data, {Delta}Belief-RL teaches information-seeking capabilities that consistently outperform purely outcome-based rewards for Reinforcement Learning, with improvements generalizing to out-of-distribution applications ranging […]

Ver mais

Jetpack Compose doesn’t “leak by default.” Most Compose leaks are plain old Kotlin reference leaks where something long-lived (a ViewModel, singleton, registry, static object, app scope coroutine) ends up holding a reference to something UI-scoped (an Activity Context, a composable lambda, a CoroutineScope, a remembered object). If you internalize one idea, make it this: Leaks happen when composition-scoped references escape into longer-lived holders. 0) The mental model you debug with Composition = runtime tree of nodes backing your […]

Ver mais

:::info Authors: Robert Avram Jeffrey E. Olgin Zeeshan Ahmed Louis Verreault-Julien Alvin Wan Joshua Barrios Sean Abreau Derek Wan Joseph E. Gonzalez Jean-Claude Tardif Derek Y. So Krishan Soni Geoffrey H. Tison ::: Abstract Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 […]

Ver mais

arXiv:2603.15691v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have given rise to vibe coding, a style of software development where developers rely on AI coding assistants to generate, modify, and refactor code using natural language instructions. While this paradigm accelerates software development and lowers barriers to entry, it introduces new challenges for quality assurance (QA). AI-generated code can appear correct but often contains hidden logical errors and inconsistencies, creating an urgent need for novel […]

Ver mais

Class imbalance, overlap, and noise degrade data quality, reduce model reliability, and limit generalization. Although widely studied in binary classification, these issues remain underexplored in multi-class settings, where complex inter-class relationships make minority-majority structures unclear and traditional clustering fails to capture distribution shape. Approaches that rely only on geometric distances risk removing informative samples and generating low-quality synthetic data, while binarization approaches treat imbalance locally and ignore global inter-class dependencies. At the algorithmic level, ensembles struggle to integrate […]

Ver mais

arXiv:2603.02230v1 Announce Type: new Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and […]

Ver mais

Human mobility prediction is a critical task but remains challenging due to its complexity and variability across populations and regions. Recently, large language models (LLMs) have made progress in zero-shot prediction, but existing methods suffer from limited interpretability (due to black-box reasoning), lack of iterative learning from new data, and poor transferability. In this paper, we introduce textbf{ARMove}, a fully transferable framework for predicting human mobility through agentic reasoning. To address these limitations, ARMove employs standardized feature management […]

Ver mais

arXiv:2602.23583v1 Announce Type: new Abstract: The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with multiple visually similar objects. To address these limitations, we propose Vision-Click-Action (VCA), a framework that replaces verbose textual commands with direct, click-based visual interaction using pretrained segmentation models. By allowing operators to specify target objects clearly through visual selection in the robot’s 2D camera view, VCA reduces […]

Ver mais