digitado

arXiv:2604.14266v1 Announce Type: new Abstract: Art-making is a collective social activity through which queer people engage in political resistance, develop identities, archive queer memory, and form community. However, in recent years, generative AI has disrupted queer artistic communities. Through 15 semi-structured interviews, we examine how queer artists are making sense of the encroachment of GenAI into their art worlds. Our findings surface significant tensions between the relationality of our participants’ queer art practices and the perceived anti-relationality of […]

Ver mais

arXiv:2604.14265v1 Announce Type: new Abstract: We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by erroneous out-of-distribution extrapolation. Existing methods either rely on reparameterized policy gradient, which are difficult to scale to large generative models, or on reject sampling, which can be overly conservative when attempting to move beyond the behavior support. In this paper, […]

Ver mais

arXiv:2604.14264v1 Announce Type: new Abstract: Highly compressible solids, such as foams, exhibit complex responses, including pronounced tension-compression asymmetry. Capturing such behaviors within unified hyperelastic frameworks remains challenging. Invariant-based hyperelastic models are commonly identified from standard tests such as homogeneous uniaxial tension/compression and simple shear, implicitly assuming a unique energy representation. Here we show that this assumption is fundamentally violated and that, oftentimes, the choice of which term should prevail is just a matter of taste. Using spline-based strain-energy […]

Ver mais

arXiv:2604.14262v1 Announce Type: new Abstract: GUI grounding models report over 85% accuracy on standard benchmarks, yet drop 27-56 percentage points when instructions require spatial reasoning rather than direct element naming. Current benchmarks miss this because they evaluate each screenshot once with a single fixed instruction. We introduce GUI-Perturbed, a controlled perturbation framework that independently varies visual scenes and instructions to measure grounding robustness. Evaluating three 7B models from the same architecture lineage, we find that relational instructions cause […]

Ver mais

arXiv:2604.14261v1 Announce Type: new Abstract: The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive, evidence-grounded feedback. We attribute this to the underutilization of two key components of human reviewing: explicit rubrics and contextual grounding in existing work. To address this, we introduce REVIEWBENCH, a benchmark evaluating review text according to paper-specific rubrics derived from official guidelines, the […]

Ver mais

arXiv:2604.14258v1 Announce Type: new Abstract: Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we provide a training-dynamics analysis showing that SFT can be interpreted as a special case of policy gradient optimization with an extremely sparse implicit reward and unstable inverse-probability weighting, which together lead to single-path dependency, entropy collapse, and gradient explosion. Motivated by this diagnosis, we […]

Ver mais

arXiv:2604.14256v1 Announce Type: new Abstract: Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems inherent to deployment. In such settings, outcomes are shaped not only by benchmark quality but also by competitive pressure, including user switching, routing decisions, and operational constraints. Yet evaluation is still largely conducted on static benchmarks with accuracy-focused measures […]

Ver mais

arXiv:2604.14254v1 Announce Type: new Abstract: The field of machine ethics aims to build Artificial Moral Agents (AMAs) to better understand morality and make AI agents safer. To do so, many approaches encode human moral intuition as a set of axioms on actions e.g., do not harm, you must help others. However, this introduces (at least) two limitations for future AMAs. First, it does not consider the agent’s purposes in performing the action. Second, it assumes that we humans […]

Ver mais

arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertainty is a poor proxy for delegation benefit, as it ignores whether the expert would actually correct the error. To address this problem, we introduce Calibrate-Then-Delegate (CTD), a model-cascade approach that provides probabilistic guarantees on the […]

Ver mais

arXiv:2604.14250v1 Announce Type: new Abstract: An important aspect of crowd monitoring is knowing how many people we are dealing with. Sometimes, knowing the size of a crowd in a single location and at a specific moment is enough. Matters become problematic when counting the same people across dif ferent locations or counting them over longer periods of time. In those cases, we need to identify and later reidentify a person, which immediately leads to privacy concerns. Until recently, […]

Ver mais