Humor Arena: Which LLM is the funniest?
We compared 20 model versions on 360 frozen joke prompts, with four jokes requested per prompt and model names hidden from our humor-trained judge. Fable 5 had the highest estimated score: 66.8 points
Knowledge catalogue
We compared 20 model versions on 360 frozen joke prompts, with four jokes requested per prompt and model names hidden from our humor-trained judge. Fable 5 had the highest estimated score: 66.8 points
arXiv:2609.18481v1 Announce Type: new Abstract: Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases
arXiv:2609.18729v1 Announce Type: cross Abstract: Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy rece
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
arXiv:2609.19138v1 Announce Type: cross Abstract: Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstration
arXiv:2609.18842v1 Announce Type: new Abstract: The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures h
arXiv:2609.17762v1 Announce Type: cross Abstract: According to Christian tradition, Luke is credited with authoring a Gospel and the Acts of the Apostles, even if his name does not appear in either bo
arXiv:2609.18955v1 Announce Type: new Abstract: Efficient perception models are essential for real-time autonomous driving, where accuracy and computational cost must be carefully balanced. However, a
Bloomberg: King Charles III hosts tech leaders, including Jensen Huang, Demis Hassabis, and OpenAI CFO Sarah Friar, to discuss AI risks; Huang calls for AI safety tests — Titans of the artificial inte
arXiv:2609.18869v1 Announce Type: new Abstract: Humanoid loco-manipulation requires robots to interpret task instructions and scene semantics while executing coordinated whole-body motions. We propose
arXiv:2609.18971v1 Announce Type: new Abstract: Surgical phase recognition maps each video frame to a clinically meaningful workflow phase, supporting context-aware assistance, documentation, and post
arXiv:2609.17628v1 Announce Type: new Abstract: Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to targe
arXiv:2609.17847v1 Announce Type: new Abstract: Learning from human feedback has become a central paradigm for training modern AI systems, where models of human utility are used as reward models in po
arXiv:2609.19040v1 Announce Type: new Abstract: Imitation learning is attractive for robot manipulation, but collecting demonstrations remains a bottleneck for multi-stage tasks requiring repeated sce
arXiv:2609.17638v1 Announce Type: cross Abstract: This is the set of lecture notes for the PhD course href{https://www.unibz.it/en/faculties/engineering/phd-computer-science/study-course-offering/2025
arXiv:2609.18148v1 Announce Type: new Abstract: The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally,
arXiv:2609.17888v1 Announce Type: cross Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This pro
arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams mo
arXiv:2609.19039v1 Announce Type: cross Abstract: We introduce the Long-Short-Range Neural Network (LSR-Net), a novel neural operator architecture designed for data-driven forward evolution modeling,
arXiv:2609.17868v1 Announce Type: new Abstract: Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathol
arXiv:2609.18445v1 Announce Type: new Abstract: Agent skills, reusable procedural documents that extend LLM agents beyond their parametric memory, have become an important interface for deploying agen
arXiv:2609.18259v1 Announce Type: cross Abstract: Recent advancements have successfully adapted autoregressive language models to process multimodal signals, such as images and actions. Since raw acti
arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history refer to different states
arXiv:2609.18961v1 Announce Type: new Abstract: Mechanistic interpretability identifies sparse subsets of heads and MLP blocks that carry specific behaviors. We ask whether such causal signals can gui
arXiv:2510.03768v2 Announce Type: replace Abstract: Data-driven planar pushing methods have recently gained attention as they reduce manual engineering effort and improve generalization compared to an
arXiv:2609.18260v1 Announce Type: new Abstract: Recent advances in artificial intelligence and computer vision are reshaping sports performance analysis by enabling automated detection, tracking, and
arXiv:2603.06084v2 Announce Type: replace Abstract: Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Visio
arXiv:2609.17987v1 Announce Type: new Abstract: The traditional Batak Ulos weaving industry faces growing challenges in producing diverse, innovative motifs due to limitations in conventional, manuall
arXiv:2603.09908v2 Announce Type: replace Abstract: Existing aerial-robotics benchmarks target vehicles from hundreds of grams to several kilograms and typically expose only high-level state data. The
arXiv:2512.09524v2 Announce Type: replace-cross Abstract: Neural decoding is fundamental to brain-computer interfaces, with growing applications in healthcare. Previous research has focused on leverag
arXiv:2609.18007v1 Announce Type: cross Abstract: Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether
arXiv:2609.17825v1 Announce Type: new Abstract: Understanding how deep neural networks make decisions remains a fundamental challenge. We present NObSP (Nonlinear Oblique Subspace Projections), a fram
arXiv:2609.18898v1 Announce Type: new Abstract: Training-free weighted aggregation is widely used to lift 2D semantic features onto 3D Gaussians for open-vocabulary scene understanding, yet its theore
arXiv:2609.18084v1 Announce Type: cross Abstract: Fine-tuning a Vision-Language-Action (VLA) model for a new deployment environment is expensive, yet most methods apply uniform-capacity adapters to ev
arXiv:2609.17942v1 Announce Type: new Abstract: The problem of identifiability in linear parametric models (LPMs) whose nodes follow either an ordered logit model or a regular one-parameter exponentia
arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use mor
arXiv:2412.00176v4 Announce Type: replace Abstract: We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investig
arXiv:2602.11220v2 Announce Type: replace-cross Abstract: Large language models are commonly adapted to downstream tasks through supervised fine-tuning (SFT), but substantial distribution mismatch bet
arXiv:2609.18120v1 Announce Type: cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, au
arXiv:2609.18025v1 Announce Type: cross Abstract: Strong chromospheric absorption lines such as Halpha 6562.8 A and Ca II 8542.1 A provide vital diagnostics of plasma dynamics and thermal structure in
arXiv:2609.19142v1 Announce Type: cross Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on divers
arXiv:2609.17846v1 Announce Type: cross Abstract: Autonomous research agents aim to automate scientific workflows, from proposing ideas to conducting experiments and analyzing results. Yet current AI
arXiv:2609.18153v1 Announce Type: new Abstract: Aerial grasping is a remarkable capability exhibited by predatory birds, allowing them to capture prey through highly coordinated maneuvers in flight. I
arXiv:2609.19077v1 Announce Type: cross Abstract: Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human c
arXiv:2609.17831v1 Announce Type: cross Abstract: Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled
arXiv:2602.02377v3 Announce Type: replace Abstract: While large language models (LLMs) have achieved strong performance on mathematical problems with verifiable answers, many advanced problems are pro
arXiv:2609.17789v1 Announce Type: cross Abstract: Quantum machine learning offers a compelling representational perspective: angle-encoded states inhabit Hilbert spaces in which periodic similarities
arXiv:2609.17995v1 Announce Type: new Abstract: Natural-language datasets support many downstream applications and research studies, but releasing text can reveal sensitive global properties of the un
arXiv:2609.18145v1 Announce Type: new Abstract: Attention pays, at every layer and for every input, the cost of searching for whom to connect. We ask how far one can get with wiring that is fixed, spa
arXiv:2609.17541v1 Announce Type: new Abstract: Service robots must respond to unexpected instructions in real-world environments. However, robots cannot detect all failures and exceptions during a ta
arXiv:2609.18359v1 Announce Type: cross Abstract: Generalized morphology control requires a single policy to transform information across limbs with different physical roles, coordinate whole-body mot
arXiv:2609.18591v1 Announce Type: new Abstract: In-context learning (ICL) enables large language model (LLM) agents to improve decisions using interaction history, yet it remains unclear whether such
arXiv:2609.18291v1 Announce Type: cross Abstract: Use case flows are important elements of use case modeling because they support downstream software engineering activities, including requirements ana
arXiv:2609.18396v1 Announce Type: cross Abstract: Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in
arXiv:2609.17555v1 Announce Type: cross Abstract: Efficient deployment of Deep Neural Networks (DNNs) on edge accelerators requires aggressive model compression while maintaining reliability in fault-
arXiv:2609.18708v1 Announce Type: cross Abstract: In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the
arXiv:2609.17788v1 Announce Type: cross Abstract: We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets
arXiv:2609.17639v1 Announce Type: cross Abstract: Modern recommendation systems largely infer user preferences from implicit behaviors such as clicks, watch time, and negative feedback, but these sign
arXiv:2609.19134v1 Announce Type: new Abstract: Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conv