arXiv:2602.03849v1 Announce Type: new Abstract: The “AI Scientist” paradigm is transforming scientific research by automating key stages of the research process, from idea generation to scholarly writing. This shift is expected to accelerate discovery and expand the scope of scientific inquiry. However, a key question remains unclear: can AI scientists identify meaningful research questions? While Large Language Models (LLMs) have been applied successfully to task-specific ideation, their potential to conduct strategic, long-term assessments of past breakthroughs and future […]

Ver mais

In this paper, we propose using Learning from Answer Sets to approximate black-box models, such as Neural Networks (NN), in the specific case of learning user preferences. We specifically explore the use of ILASP (Inductive Learning of Answer Set Programs) to approximate preference learning systems through weak constraints. We have created a dataset on user preferences over a set of recipes, which is used to train the NNs that we aim to approximate with ILASP. Our experiments investigate […]

Ver mais

arXiv:2512.20305v2 Announce Type: replace Abstract: Accelerated failure time (AFT) models provide a direct and interpretable time-scale description of covariate effects in lifetime data analysis, but classical formulations rely on linear predictors and are therefore limited in their ability to represent nonlinear relationships. Moreover, in heterogeneous clinical settings with complex covariate structures and varying censoring mechanisms, standard survival models such as the Cox proportional hazards model or AFT formulations may be inadequate due to restrictive structural assumptions. We propose […]

Ver mais

arXiv:2604.01263v1 Announce Type: new Abstract: The computational equivalence between approximate counting and sampling is well established for polynomial-time algorithms. The most efficient general reduction from counting to sampling is achieved via simulated annealing, where the counting problem is formulated in terms of estimating the ratio $Q={Z(beta_{max})}/{Z(beta_{min})}$ between partition functions $Z(beta)=sum_{xin Omega} exp(beta H(x))$ of Gibbs distributions $mu_beta$ over $Omega$ with Hamiltonian $H$, given access to a sampling oracle that produces samples from $mu_beta$ for $beta in [beta_{min}, beta_{max}]$. […]

Ver mais

Hi everyone, I’m a 3rd-year undergraduate student currently working on a reinforcement learning project. My goal is to train a WLKATA Mirobot (6-DOF) in NVIDIA Isaac Lab for a “reach and stop” task and successfully transfer the policy to the real robot (Sim-to-Real). I am specifically focusing on overcoming the mechanical limitations (such as backlash and joint friction) of the Mirobot through Domain Randomization and System Identification. Before I dive deeper into designing the environment, I wanted to […]

Ver mais

In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts, we study demonstration-dependent tasks requiring models to infer underlying patterns, a process we characterize as rule inference. We find that models suffer substantial performance degradation from a single demonstration with corrupted rule. This systematic misleading behavior motivates our investigation of how models process […]

Ver mais

arXiv:2602.07050v1 Announce Type: new Abstract: A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variables in order to make physically accurate predictions, or whether they can implicitly represent such variables in a task-specific, distributed manner. While modern video world models achieve strong performance on intuitive physics benchmarks, it remains unclear which of these representational regimes they implement internally. Here, we present the first interpretability study to directly examine physical […]

Ver mais

arXiv:2603.00549v1 Announce Type: new Abstract: We present PM2Lat, a fast and generalized framework for accurately predicting the latency of deep neural network models on GPUs, with special focus on NVIDIA. Unlike prior methods that rely on deep learning models or handcrafted heuristics, PM2Lat leverages the Single-Instruction-Multiple-Thread architecture of GPUs to model execution time of DNN models. First, we dive into fine-grained GPU operation modeling by studying computational behavior and memory access patterns. After identifying these characteristics, we found […]

Ver mais