arXiv:2603.06768v2 Announce Type: replace Abstract: Genotype-to-phenotype prediction is a central goal of statistical genetics, yet practical comparisons of prediction workflows remain limited in small, heterogeneous, participant-shared genomic datasets. Here, we benchmarked end-to-end case-control prediction across 80 curated binary phenotypes from openSNP using machine learning, deep learning, and polygenic score workflows. We evaluated 29 machine-learning algorithms, […]
From Context to Skills: Can Language Models Learn from Context Skillfully?
arXiv:2604.27660v2 Announce Type: replace Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, […]
Riemannian Generative Decoder
arXiv:2506.19133v3 Announce Type: replace-cross Abstract: Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embedding data onto matching manifolds, it typically relies on an encoder to estimate densities on chosen manifolds. This involves optimizing numerically brittle objectives, potentially harming model training and quality. To completely circumvent this issue, […]
Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models
arXiv:2510.23633v2 Announce Type: replace-cross Abstract: Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation information into the generation process of the diffusion models. However, this presents an inherent dilemma: excessive integration can disrupt the generative process, while insufficient integration fails to emphasize the constraints imposed by the inverse problem. […]
Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
arXiv:2601.19963v3 Announce Type: replace-cross Abstract: Training a high-performing neural decoder can be difficult when only limited data are available from a recording session. To address this challenge, we propose a Task-Conditioned Latent Alignment framework (TCLA) for cross-session neural decoding with limited target-session data. Building upon an autoencoder architecture, TCLA first learns a low-dimensional neural representation […]
How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
arXiv:2512.12688v3 Announce Type: replace-cross Abstract: Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts function as semantic conditions on how a fixed model interprets inputs, foregrounds information, […]
LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
arXiv:2603.00042v2 Announce Type: replace-cross Abstract: We identify the Spectral Energy Gain in extreme model compression, where low-rank binary approximations outperform tiny-rank floating-point baselines for heavy-tailed spectra. However, prior attempts fail to realize this potential, trailing state-of-the-art 1-bit methods. We attribute this degradation to Latent Geometry Misalignment: standard singular vectors exhibit high coherence (spiky distribution), the […]
VoodooNet: Achieving Analytic Ground States via High-Dimensional Random Projections
arXiv:2604.15613v3 Announce Type: replace-cross Abstract: We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic solution via Galactic Expansion. By projecting input manifolds into a high-dimensional, high-entropy “Galactic” space ($d gg 784$), we demonstrate that complex features can be untangled without the thermodynamic cost of backpropagation. […]
Principles and Guidelines for Randomized Controlled Trials in AI Evaluation
arXiv:2605.02050v1 Announce Type: cross Abstract: This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established experimental practices from disciplines with established RCT traditions, including software engineering, economics, clinical and health sciences, and psychology, we adopt the (Shadish et al., 2002) four-validity framework and extend it with […]
RAFNet: Region-Aware Fusion Network for Pansharpening
arXiv:2605.02184v1 Announce Type: cross Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images. Although deep learning has advanced this field, mainstream frequency-based methods relying on standard scaled dot-product attention suffer from quadratic computational complexity and fail to exploit the inherent regional sparsity of remote sensing […]
Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning
arXiv:2605.02372v1 Announce Type: cross Abstract: The growing development of artificial intelligence based solutions, together with privacy legislation, has driven the rise of the so-called privacy preserving machine learning architectures, such as federated learning. While federated learning enables model training on decentralized data preventing their sharing and centralization, it still faces several challenges related to data […]
Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
arXiv:2605.02520v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) offers a well-established path to grounding large language model (LLM) outputs in external knowledge, yet the question of which retrieval strategy works best in a high-stakes domain such as biomedicine has not received the controlled, multi-metric treatment it deserves. This paper presents a systematic empirical comparison of […]