Parallel to the development of advanced deepfake audio generation, audio deepfake detection has also seen significant progress. However, a standardized and comprehensive benchmark is still missing. To address this, we introduce Speech DeepFake (DF) Arena, the first comprehensive benchmark for audio deepfake detection. Speech DF Arena provides a toolkit to uniformly evaluate detection systems, currently across 14 diverse datasets and attack scenarios, standardized evaluation metrics and protocols for reproducibility and transparency. It also includes a leaderboard to compare and rank the systems to help researchers and developers enhance their reliability and robustness. We include 14 evaluation sets, 12 state-of-the-art open-source and 3 proprietary detection systems. Our study presents many systems exhibiting high EER in out-of-domain scenarios, highlighting the need for extensive cross-domain evaluation. The leaderboard is hosted on Huggingface1 and a toolkit for reproducing results across the listed datasets is available on GitHub.

Colon cancer also known as Colorectal cancer, is one of the most malignant types of cancer worldwide. Early-stage detection of colon cancer is highly crucial to prevent its deterioration. This research presents a hybrid multi-scale deep learning architecture that synergizes capsule networks, graph attention mechanisms, transformer modules, and residual learning to advance colon cancer classification on the Lung and Colon Cancer Histopathological Image Dataset (LC25000) dataset. The proposed model in this paper utilizes the HG-TNet model that introduces a hybrid architecture that joins strength points in transformers and convolutional neural networks to capture multi-scale features in histopathological images. Mainly, a transformer branch extracts global contextual bonds by partitioning the image into patches by convolution-based patch embedding and then processing these patches through a transformer encoder. Analogously, a dedicated CNN branch captures fine-grained, local details through successive Incorporation these diverse features, combined with a self-supervised rotation prediction objective, produce a robust diagnostic representation that surpasses standard architectures in performance. Results show better performance not only in accuracy or loss function but also in these algorithms by utilizing capsule networks to preserve spatial orders and realize how each element individually combines and forms whole structures.

Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization.

This study investigates how large language models, in particular LLaMA 3.2-3B, construct narratives about Black and white women in short stories generated in Portuguese. From 2100 texts, we applied computational methods to group semantically similar stories, allowing a selection for qualitative analysis. Three main discursive representations emerge: social overcoming, ancestral mythification and subjective self-realization. The analysis uncovers how grammatically coherent, seemingly neutral texts materialize a crystallized, colo-nially structured framing of the female body, reinforcing historical inequalities. The study proposes an integrated approach, that combines machine learning techniques with qualitative, manual discourse analysis.

Combinatorial methods for learning general policies that solve large collections of planning problems have been recently developed. One of their strengths, in relation to deep learning approaches, is that the resulting policies can be understood and shown to be correct. A weakness is that the methods do not scale up and learn only from small training instances and feature pools that contain a few hundreds of states and features at most. In this work, we propose a new symbolic method for learning policies based on the generalization of sampled plans that ensures structural termination and hence acyclicity. The proposed learning approach is not based on SA T/ASP, as previous symbolic methods, but on a hitting set algorithm that can effectively handle problems with millions of states, and pools with hundreds of thousands of features. The formal properties of the approach are analyzed, and its scalability is tested on a number of benchmarks.

Existing approaches to predictive uncertainty rely either on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation, or on ensemble learning, which improves accuracy but rarely captures the structured ambiguity. This implicitly means that a unified framework consistent with the loss geometry remains absent. The Structured Basis Function Network addresses this gap by linking multi-hypothesis prediction and ensembling through centroidal aggregation induced by Bregman divergences. The formulation applies across regression and classification by aligning predictions with the geometry of the loss, and supports both a closed-form least-squares estimator and a gradient-based procedure for general objectives. A tunable diversity mechanism provides parametric control of the bias-variance-diversity trade-off, connecting multi-hypothesis generalisation with loss-aware ensemble aggregation. Experiments validate this relation and use the mechanism to study the complexity-capacity-diversity trade-off across datasets of increasing difficulty with deep-learning predictors.

In parallel with the recent breakthroughs in large language models [1, 2], Transformer-based approaches have also achieved widespread success in the domain of autonomous driving motion generation, including tasks such as trajectory prediction [3, 4, 5], traffic simulation [6, 7, 8], and ego-vehicle planning [9, 10, 11]. However, most prior works have focused on empirically transferring individual modules from LLMs to autonomous driving applications. In contrast, this paper takes a more holistic perspective to explore the striking similarities between LLMs and autonomous driving motion generation, while also highlighting the subtle differences that lie beneath these similarities. Autonomous driving motion generation refers to the task of generating future trajectories for specified agents under a set of constraints, based on contextual information from the environment and the historical states of the agents. Transformer-based models--particularly those following the GPT architecture--have achieved considerable success in this domain in recent years [8, 12, 13, 14]. Their typical workflows encompass only a subset of the overall modeling process, consisting of the following components: T okenizing: compressing contextual and motion information into a sequence of tokens that can later be decoded into trajectories; Positional Embedding: encoding spatial and temporal relationships among agents, between agents and the environment, and within each agent's trajectory; Pre-training: training the model on large-scale self-supervised datasets to learn gener-alizable motion generation capabilities; Post-training: applying fine-tuning techniques to enforce additional constraints, such as collision avoidance or human-like behavior; T est-time Computing: leveraging increased compute budgets to dynamically optimize model outputs without modifying model parameters during inference.

This work explores the potential of foundation models, specifically a Mamba-based selective state space model, for enhancing EEG analysis in neurological disorder diagnosis. EEG, crucial for diagnosing conditions like epilepsy, presents significant challenges due to its noisy, high-dimensional, and nonlinear nature. Traditional machine learning methods have made advances in automating EEG analysis but often fail to capture its complex spatio-temporal dynamics. Recent advances in deep learning, particularly in sequence modeling, offer new avenues for creating more generalized and expressive models capable of handling such complexities. By training a Mamba-based model on a large dataset containing seizure and non-seizure EEG recordings through a self-supervised reconstruction task followed by a seizure detection task, we demonstrate the model's effectiveness, achieving an AUROC of 0.72 on a held-out test set. This approach marks a significant step toward developing large-scale, clinically applicable foundation models for EEG data analysis.

Recent advances in generative biology have enabled the design of novel proteins, creating significant opportunities for drug discovery while also introducing new risks, including the potential development of synthetic bioweapons. Existing biosafety measures primarily rely on inference-time filters such as sequence alignment and protein-protein interaction (PPI) prediction to detect dangerous outputs. In this study, we evaluate the performance of three leading PPI prediction tools: AlphaFold 3, AF3Complex, and SpatialPPIv2. These models were tested on well-characterized viral-host interactions, such as those involving Hepatitis B and SARS-CoV-2. Despite being trained on many of the same viruses, the models fail to detect a substantial number of known interactions. Strikingly, none of the tools successfully identify any of the four experimentally validated SARS-CoV-2 mutants with confirmed binding. These findings suggest that current predictive filters are inadequate for reliably flagging even known biological threats and are even more unlikely to detect novel ones. We argue for a shift toward response-oriented infrastructure, including rapid experimental validation, adaptable biomanufacturing, and regulatory frameworks capable of operating at the speed of AI-driven developments.

Accurate and robust environmental perception is crucial for robot autonomous navigation. While current methods typically adopt optical sensors (e.g., camera, LiDAR) as primary sensing modalities, their susceptibility to visual occlusion often leads to degraded performance or complete system failure. In this paper, we focus on agricultural scenarios where robots are exposed to the risk of onboard sensor contamination. Leveraging radar's strong penetration capability, we introduce a radar-based 3D environmental perception framework as a viable alternative. It comprises three core modules designed for dense and accurate semantic perception: 1) Parallel frame accumulation to enhance signal-to-noise ratio of radar raw data. 2) A diffusion model-based hierarchical learning framework that first filters radar sidelobe artifacts then generates fine-grained 3D semantic point clouds. 3) A specifically designed sparse 3D network optimized for processing large-scale radar raw data. We conducted extensive benchmark comparisons and experimental evaluations on a self-built dataset collected in real-world agricultural field scenes. Results demonstrate that our method achieves superior structural and semantic prediction performance compared to existing methods, while simultaneously reducing computational and memory costs by 51.3% and 27.5%, respectively. Furthermore, our approach achieves complete reconstruction and accurate classification of thin structures such as poles and wires-which existing methods struggle to perceive-highlighting its potential for dense and accurate 3D radar perception.