arXiv:2602.02548v1 Announce Type: new Abstract: Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under severe data scarcity. To address the limitations, we propose ToolTok, a novel paradigm of multi-step pathfinding for GUI agents, where operations are modeled as a sequence of progressive tool usage. Specifically, we devise tools aligned with human interaction habits and represent each tool using […]

Ver mais

For six months, I was forwarding YouTube links with messages like watch this when you get a chance. Nobody watched them. I know because I checked. I run a PR agency. Fifteen people spread across multiple cities, handling 90+ clients, pushing out content across 100+ websites. The kind of operation where every saved hour compounds. So when AI tools started getting genuinely capable – not just demo-reel capable – I wanted my team on board fast. My first […]

Ver mais

arXiv:2603.02238v1 Announce Type: new Abstract: Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a guarantee, one needs to be able to compute a length generalization bound, beyond which the model is guaranteed to generalize. This paper concerns the open problem of the computability of such generalization bounds for CRASP, a class of languages which is closely linked […]

Ver mais

arXiv:2602.10608v1 Announce Type: new Abstract: Policy inference plays an essential role in the contextual bandit problem. In this paper, we use empirical likelihood to develop a Bayesian inference method for the joint analysis of multiple contextual bandit policies in finite sample regimes. The proposed inference method is robust to small sample sizes and is able to provide accurate uncertainty measurements for policy value evaluation. In addition, it allows for flexible inferences on policy comparison with full uncertainty quantification. […]

Ver mais

Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models become excessively over-confident in incorrect answers. Previous studies devote to directly incorporating calibration objective into existing optimization target. However, our theoretical analysis demonstrates that there exists a fundamental gradient conflict between the optimization for maximizing policy accuracy and minimizing calibration error. Building on this insight, we propose DCPO, a simple yet effective framework that systematically decouples reasoning […]

Ver mais

arXiv:2508.07465v2 Announce Type: replace-cross Abstract: Integrating multi-omics data, such as DNA methylation, mRNA expression, and microRNA (miRNA) expression, offers a comprehensive view of the biological mechanisms underlying disease. However, the high dimensionality of multi-omics data, the heterogeneity across modalities, and the lack of reliable biological interaction networks make meaningful integration challenging. In addition, many existing models rely on handcrafted similarity graphs, are vulnerable to class imbalance, and often lack built-in interpretability, limiting their usefulness in biomedical applications. We […]

Ver mais

Hey hackers!  If you’ve ever wondered why some of your submissions take a while before they get published, it’s probably because you’re submitting incomplete articles.  While most contributors focus on the content and the headline, we often receive submissions that are missing their meta, TL;dr, and keyword sections. Worse yet, sometimes contributors will add some keywords but not maximize the space for some of that SEO goodness.  As we start the new year, the editorial team thinks it’s […]

Ver mais

Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unlike standard locomotion or static manipulation, this task demands a seamless integration of explosive whole-body coordination and precise, timing-critical interception. While recent advances have achieved lifelike motion mimicry, bridging the gap between kinematic imitation and functional, physics-aware striking without compromising stylistic naturalness is non-trivial. To address this, we propose Imitation-to-Interaction, a progressive reinforcement learning framework designed to evolve a robot from […]

Ver mais

The extraction pipeline processed 2,400 documents overnight. Cost: $380. The next morning I diffed the inputs against the previous batch—87% were near-duplicates with trivial whitespace changes. I’d burned $330 re-extracting answers I already had. Not because the cache missed. Because my cache had no right to hit. A TTL can tell you when something is old. It cannot tell you when something is wrong. And for an AI extraction pipeline, “wrong” is the only thing that matters. So […]

Ver mais