arXiv:2508.03593v2 Announce Type: replace Abstract: Feature selection (FS) is assumed to improve predictive performance and identify meaningful features in high-dimensional datasets. Surprisingly, small random subsets of features (0.02-1%) match or outperform the predictive performance of both full feature sets and…
arXiv:2508.05244v2 Announce Type: replace-cross Abstract: Medical image understanding plays a crucial role in enabling automated diagnosis and data-driven clinical decision support. However, its progress is impeded by two primary challenges: the limited availability of high-quality annotated medical data and an…
arXiv:2505.24544v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on tightly coupled,…
arXiv:2405.18848v3 Announce Type: replace-cross Abstract: Anomaly detection focuses on identifying samples that deviate from the norm. Discovering informative representations of normal samples is crucial to detecting anomalies effectively. Recent self-supervised methods have successfully learned such representations by employing prior knowledge…
arXiv:2501.13951v3 Announce Type: replace-cross Abstract: Long-form mental health assessments pose unique challenges for large language models (LLMs), which often exhibit hallucinations or inconsistent reasoning when handling extended, domain-specific contexts. We introduce Stacked Multi-Model Reasoning (SMMR), a layered framework that leverages…
arXiv:2509.15541v1 Announce Type: new Abstract: Highly capable AI systems could secretly pursue misaligned goals — what we call “scheming”. Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different strategies…
arXiv:2503.23781v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong potential and impressive performance in automating the generation and optimization of workflows. However, existing approaches are marked by limited reasoning capabilities, high computational demands, and significant resource requirements.…
arXiv:2509.15366v1 Announce Type: new Abstract: The rapid evolution of neural architectures – from multilayer perceptrons to large-scale Transformer-based models – has enabled language models (LLMs) to exhibit emergent agentic behaviours when equipped with memory, planning, and external tool use. However,…
arXiv:2509.15409v1 Announce Type: new Abstract: Retrosynthesis, the process of deconstructing a target molecule into simpler precursors, is crucial for computer-aided synthesis planning (CASP). Widely adopted tree-search methods often suffer from exponential computational complexity. In this work, we introduce FragmentRetro, a…
arXiv:2509.15336v1 Announce Type: new Abstract: The utility of Large Language Models (LLMs) in analytical tasks is rooted in their vast pre-trained knowledge, which allows them to interpret ambiguous inputs and infer missing information. However, this same capability introduces a critical…
