Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,736 papers.
27 Oct 2026
When expanding a report, writing with agents may introduce a stronger claim than the article makes and then disclaim it. This is called over-defensive writing. We assume that this is because the agent is writing for responding to an adversarial AI reviewer, instead of a human…
27 Oct 2026
Do vision-language models (VLMs) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models…
27 Oct 2026
The Asch conformity experiment has recently gained considerable attention as a way of measuring conformity in large language models (LLMs). While previous studies have focused on demonstrating conformity in LLMs, our work adds a further quantitative layer to this approach.
26 Oct 2026
We measure, without sampling error, the probability a language model assigns to each integer from 1 to N when asked for a random number. For a fixed prompt the model defines one probability vector, which we compute by summing over each integer's scored spellings rather than…
26 Oct 2026
Machine learning systems trained on untrusted data are vulnerable to data and backdoor poisoning attacks, in which an adversary corrupts training and test samples to manipulate predictions at inference time.
26 Oct 2026
Ambiguity in prescriptive text such as laws, contracts, rules, policies, or recommendations can be both desirable (e.g., if it enables a law to adapt to changing context, such as new technologies) and undesirable (e.g., if it leads to arbitrary discretion or conflict over the…
26 Oct 2026
A graph neural network (GNN) forecasting a collection of load series combines two mechanisms, sharing parameters across series and reading neighboring series, and a gain over a non-graph model may come from either; telling them apart decides whether a graph is worth maintaining.
26 Oct 2026
Wind farm layout optimization becomes increasingly difficult as turbine count grows, especially when high-fidelity aerodynamic models are used. Conventional Kriging-based Bayesian optimization often suffers from low sample efficiency in high-dimensional layout spaces because…
26 Oct 2026
Environmental noise identification is essential for noise control, yet conventional single-stage classifiers suffer from class confusion under imbalanced multiclass conditions.
26 Oct 2026
Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies.
26 Oct 2026
Automatic modulation classification (AMC) of radio signals is a core technology for spectrum monitoring and electromagnetic situational awareness. Deep neural networks (DNNs) play an important role in this field owing to their powerful feature extraction capabilities and…
26 Oct 2026
Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process.
26 Oct 2026
Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices.
25 Oct 2026
"Data quality" is widely invoked in instruction tuning, but the term is often underspecified. We study it as an operational property by asking which simple example-level metrics, drawn from prior work on data selection, text quality, and instruction tuning, best predict…
25 Oct 2026
In this paper, we introduce $Δτ$-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In $Δτ$-Bench, independently evolving services continually reshape how tasks can be accomplished: familiar tools may disappear or be replaced,…
25 Oct 2026
We release a battery of 28 propensities for AI research, with expert-written rubrics, synthetic datasets, and annotated demand intervals, built with the method of Romero-Alvarado et al. (2026).
25 Oct 2026
Feature analysis is a crucial step in medical image analysis, particularly in breast cancer classification. Traditional image analysis methods often struggle with optimal patterns along the diagonal axis, computational efficiency and feature buffer storage.
25 Oct 2026
Scientific literature in materials physics is growing faster than researchers can manually inspect it, yet most retrieval tools rely on keyword matching or generic question answering that ignores domain-specific structure in PDF files.
25 Oct 2026
We propose a joint sparse sample weighting and parameter estimation (SWAPE) framework that jointly optimizes model parameters and sample weights to train a model while simultaneously assigning an individual weight to each training data point.
25 Oct 2026
Large Language Models(LLMs) have shown strong performance on tasks with verifiable answers, but many real-world queries involve subjectivity, disagreement, and conflicting evidence.
25 Oct 2026
Entropy in reinforcement learning with verifiable rewards (RLVR) moves up or down depending on choices that should be neutral, such as whether over-length responses are masked or counted as failures.
24 Oct 2026
The capabilities of large language models (LLMs) and multimodal LLMs (MLLMs) arise from the synergy of the full training pipeline, including data and tokenization, pretraining, and post-training (supervised fine-tuning, preference alignment, reinforcement learning, and continual…
24 Oct 2026
In this work, we propose a unified framework for training algorithms across different stages of modern large language model development, based on the perspective of distribution matching.
24 Oct 2026
This paper presents a model theoretic and computational formalization of AlKhwarizmis treatment of inheritance within the framework of Computational Fiqh. We first show that every inheritance configuration in a specified class is representable as a finite system of rational…