Progress in computer-aided synthesis planning (CASP) is obscured by the lack of standardized evaluation infrastructure and the reliance on metrics that prioritize topological completion over chemical validity. We introduce RetroCast, a unified evaluation suite that standardizes heterogeneous model outputs into a common schema to enable statistically rigorous, apples-to-apples comparison. The framework includes a reproducible benchmarking pipeline with stratified sampling and bootstrapped confidence intervals, accompanied by SynthArena, an interactive platform for qualitative route inspection. We utilize this infrastructure to evaluate leading search-based and sequence-based algorithms on a new suite of standardized benchmarks. Our analysis reveals a divergence between "solvability" (stock-termination rate) and route quality; high solvability scores often mask chemical invalidity or fail to correlate with the reproduction of experimental ground truths. Furthermore, we identify a "complexity cliff" in which search-based methods, despite high solvability rates, exhibit a sharp performance decay in reconstructing long-range synthetic plans compared to sequence-based approaches. We release the full framework, benchmark definitions, and a standardized database of model predictions to support transparent and reproducible development in the field.

In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks for evaluating whether LLMs genuinely possess this capability suffer from three key limitations: a lack of contextual scenarios, insufficient cross-cultural concept mapping, and limited deep cultural reasoning capabilities. To address these gaps, we propose SAGE, a scenario-based benchmark built via cross-cultural core concept alignment and generative task design, to evaluate LLMs' cross-cultural understanding and reasoning. Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions. Using this framework, we curated 210 core concepts and constructed 4530 test items across 15 specific real-world scenarios, organized under four broader categories of cross-cultural situations, following established item design principles. The SAGE dataset supports continuous expansion, and experiments confirm its transferability to other languages. It reveals model weaknesses across both dimensions and scenarios, exposing systematic limitations in cross-cultural reasoning. While progress has been made, LLMs are still some distance away from reaching a truly nuanced cross-cultural understanding. In compliance with the anonymity policy, we include data and code in the supplement materials. In future versions, we will make them publicly available online.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.

Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves all three capabilities within a single hierarchical predictive-coding recurrent neural network (PC-RNN) equipped with a class embedding vector, CERNet, which leverages a dynamically updated class embedding vector to unify motor generation and recognition. The model operates in two modes: generation and inference. In the generation mode, the class embedding constrains the hidden state dynamics to a class-specific subspace; in the inference mode, it is optimized online to minimize prediction error, enabling real-time recognition. Validated on a humanoid robot across 26 kinesthetically taught alphabets, our hierarchical model achieves 76% lower trajectory reproduction error than a parameter-matched single-layer baseline, maintains motion fidelity under external perturbations, and infers the demonstrated trajectory class online with 68% Top-1 and 81% Top-2 accuracy. Furthermore, internal prediction errors naturally reflect the model's confidence in its recognition. This integration of robust generation, real-time recognition, and intrinsic uncertainty estimation within a compact PC-RNN framework offers a compact and extensible approach to motor memory in physical robots, with potential applications in intent-sensitive human-robot collaboration.

Complex biological networks are fundamental to biomedical science, capturing interactions among molecules, cells, genes, and tissues. Deciphering these networks is critical for understanding health and disease, yet their scale and complexity represent a daunting challenge for current computational methods. Traditional biological network analysis methods, including deep learning approaches, while powerful, face inherent challenges such as limited scalability, oversmoothing long-range dependencies, difficulty in multimodal integration, expressivity bounds, and poor interpretability. We present Graph2Image, a framework that transforms large biological networks into sets of two-dimensional images by spatially arranging representative network nodes on a 2D grid. This transformation decouples the nodes as images, enabling the use of convolutional neural networks (CNNs) with global receptive fields and multi-scale pyramids, thus overcoming limitations of existing biological network analysis methods in scalability, memory efficiency, and long-range context capture. Graph2Image also facilitates seamless integration with other imaging and omics modalities and enhances interpretability through direct visualization of node-associated images. When applied to several large-scale biological network datasets, Graph2Image improved classification accuracy by up to 67.2% over existing methods and provided interpretable visualizations that revealed biologically coherent patterns. It also allows analysis of very large biological networks (nodes > 1 billion) on a personal computer. Graph2Image thus provides a scalable, interpretable, and multimodal-ready approach for biological network analysis, offering new opportunities for disease diagnosis and the study of complex biological systems.

Glass is a prevalent material among solid objects in everyday life, yet segmentation methods struggle to distinguish it from opaque materials due to its transparency and reflection. While it is known that human perception relies on boundary and reflective-object features to distinguish glass objects, the existing literature has not yet sufficiently captured both properties when handling transparent objects. Hence, we propose incorporating both of these powerful visual cues via the Boundary Feature Enhancement and Reflection Feature Enhancement modules in a mutually beneficial way. Our proposed framework, TransCues, is a pyramidal transformer encoder-decoder architecture to segment transparent objects. W e empirically show that these two modules can be used together effectively, improving overall performance across various benchmark datasets, including glass object semantic segmentation, mirror object semantic segmentation, and generic segmentation datasets.

Among the various types of cyberattacks, identifying zero-day attacks is problematic because they are unknown to security systems as their pattern and characteristics do not match known blacklisted attacks. There are many Machine Learning (ML) models designed to analyze and detect network attacks, especially using supervised models. However, these models are designed to classify samples (normal and attacks) based on the patterns they learn during the training phase, so they perform inefficiently on unseen attacks. This research addresses this issue by evaluating five different supervised models to assess their performance and execution time in predicting zero-day attacks and find out which model performs accurately and quickly. The goal is to improve the performance of these supervised models by not only proposing a framework that applies grid search, dimensionality reduction and oversampling methods to overcome the imbalance problem, but also comparing the effectiveness of oversampling on ml model metrics, in particular the accuracy. To emulate attack detection in real life, this research applies a highly imbalanced data set and only exposes the classifiers to zero-day attacks during the testing phase, so the models are not trained to flag the zero-day attacks. Our results show that Random Forest (RF) performs best under both oversampling and non-oversampling conditions, this increased effectiveness comes at the cost of longer processing times. Therefore, we selected XG Boost (XGB) as the top model due to its fast and highly accurate performance in detecting zero-day attacks.

Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy information, leading to poor retrieval accuracy. Recent advances in large language models (LLMs) have improved bug localization through query reformulation, yet the effect on agent performance remains unexplored. In this study, we investigate how an LLM-powered agent can improve file-level bug localization via lightweight query reformulation and summarization. We first employ an open-source, non-fine-tuned LLM to extract key information from bug reports, such as identifiers and code snippets, and reformulate queries pre-retrieval. Our agent then orchestrates BM25 retrieval using these preprocessed queries, automating localization workflow at scale. Using the best-performing query reformulation technique, our agent achieves 35% better ranking in first-file retrieval than our BM25 baseline and up to +22% file retrieval performance over SWE-agent.

Deep learning models have shown high accuracy in classifying electrocardiograms (ECGs), but their black box nature hinders clinical adoption due to a lack of trust and interpretability. To address this, we propose a novel three-stage training paradigm that transfers knowledge from multimodal clinical data (laboratory exams, vitals, biometrics) into a powerful, yet unimodal, ECG encoder. We employ a self-supervised, joint-embedding pre-training stage to create an ECG representation that is enriched with contextual clinical information, while only requiring the ECG signal at inference time. Furthermore, as an indirect way to explain the model's output we train it to also predict associated laboratory abnormalities directly from the ECG embedding. Evaluated on the MIMIC-IV-ECG dataset, our model outperforms a standard signal-only baseline in multi-label diagnosis classification and successfully bridges a substantial portion of the performance gap to a fully multimodal model that requires all data at inference. Our work demonstrates a practical and effective method for creating more accurate and trustworthy ECG classification models. By converting abstract predictions into physiologically grounded \emph{explanations}, our approach offers a promising path toward the safer integration of AI into clinical workflows.

Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block-Sparse FlashAttention (BSFA), a drop-in replacement that accelerates long-context inference while preserving model quality. Unlike methods that predict importance before computing scores, BSFA computes exact query-key similarities to select the top-k most important value blocks for each query. By comparing per-block maximum scores against calibrated thresholds, we skip approximately 50% of the computation and memory transfers for pruned blocks. Our training-free approach requires only a one-time threshold calibration on a small dataset to learn the per-layer and per-head attention score distributions. We provide a CUDA kernel implementation that can be used as a drop-in replacement for FlashAttention. On Llama-3.1-8B, BSFA achieves up to 1.10x speedup on real-world reasoning benchmarks and up to 1.24x for needle-in-a-haystack retrieval tasks while maintaining above 99% baseline accuracy, with certain configurations even improving accuracy by focusing on the most relevant content, substantially outperforming existing sparse attention methods. The implementation is available at https://github.com/Danielohayon/Block-Sparse-Flash-Attention