Provenance Brief

Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding order.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Computational point-of-care (POC) sensors enable rapid, low-cost, and accessible diagnostics in emergency, remote and resource-limited areas that lack access to centralized medical facilities.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Separating signal from noise is central to experimental science.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

We propose Parallel Token Prediction (PTP), a universal framework for parallel sequence generation in language models.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

This paper derives `Scaling Laws for Economic Impacts' -- empirical relationships between the training compute of Large Language Models (LLMs) and professional productivity.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/triangle meshes while modern 3D assets increasingly live as…

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Acute Myeloid Leukemia (AML) remains a clinical challenge due to its extreme molecular heterogeneity and high relapse rates.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely unexplored.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

The user of Engineering Manuals (EM) finds it difficult to read EM s because they are long, have a dense format which includes written documents, step by step procedures, and standard parameter lists for engineering…

Builder: scan the abstract + experiments; look for code, datasets, and evals.

The increasing integration of AI tools in education has led prior research to explore their impact on learning processes.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Methods that use Large Language Models (LLM) as planners for embodied instruction following tasks have become widespread.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to practical deployment.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

In this work, we introduce PhononBench, the first large-scale benchmark for dynamical stability in AI-generated crystals.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Retrieving images from natural language descriptions is a core task at the intersection of computer vision and natural language processing, with wide-ranging applications in search engines, media archiving, and…

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Attribution modelling lies at the heart of marketing effectiveness, yet most existing approaches depend on user-level path data, which are increasingly inaccessible due to privacy regulations and platform restrictions.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-supervised speech models.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Zero-shot object navigation (ZSON) requires a robot to locate a target object in a previously unseen environment without relying on pre-built maps or task-specific training.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

We consider the problem of ranking $n$ experts according to their abilities, based on the correctness of their answers to $d$ questions.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

The empirical success of deep learning is often attributed to scaling laws that predict consistent gains as model, data, and compute grow; however, large models can exhibit training instability and diminishing…

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Diffusion models are a class of generative models that have demonstrated remarkable success in tasks such as image generation.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Modeling sparse count data, which arise across numerous scientific fields, presents significant statistical challenges.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

A methodology is developed to extract $d$ invariant features $W=f(X)$ that predict a response variable $Y$ without being confounded by variables $Z$ that may influence both $X$ and $Y$.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Several performance measures are used to evaluate binary and multiclass classification tasks.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

We study the problem of subgroup discovery for survival analysis, where the goal is to find an interpretable subset of the data on which a Cox model is highly accurate.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

We present GeoTransolver, a Multiscale Geometry-Aware Physics Attention Transformer for CAE that replaces standard attention with GALE, coupling physics-aware self-attention on learned state slices with…

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Plant diseases pose a significant threat to global food security, necessitating accurate and interpretable disease detection methods.

Builder: scan the abstract + experiments; look for code, datasets, and evals.

Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity.

Builder: scan the abstract + experiments; look for code, datasets, and evals.