arXiv:2506.18919v4 Announce Type: replace-cross Abstract: As a multimodal medium combining images and text, memes frequently convey implicit harmful content through metaphors and humor, rendering the detection of harmful memes a complex and challenging task. Although recent studies have made progress in detection accuracy and interpretability, large-scale, high-quality datasets for harmful memes remain scarce, and current […]
Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation
arXiv:2512.02413v3 Announce Type: replace-cross Abstract: Automatic 3D reconstruction of indoor spaces from 2D floor plans necessitates high-precision semantic segmentation of structural elements, particularly walls. However, existing methods often struggle with detecting thin structures and maintaining geometric precision. To address this, we introduce MitUNet, a hybrid neural network designed to bridge the gap between global semantic […]
SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization
arXiv:2603.17219v2 Announce Type: replace-cross Abstract: Multi-site neuroimaging analysis is fundamentally confounded by scanner-induced covariate shifts, where the marginal distribution of voxel intensities $P(mathbfx)$ varies non-linearly across acquisition protocols while the conditional anatomy $P(mathbfy|mathbfx)$ remains constant. This is particularly detrimental to radiomic reproducibility, where acquisition variance often exceeds biological pathology variance. Existing statistical harmonization methods (e.g., […]
Fast and Accurate Probing of In-Training LLMs’ Downstream Performances
arXiv:2604.01025v1 Announce Type: cross Abstract: The paradigm of scaling Large Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive, therefore making the latency of LLM’s in-training downstream performance evaluation unbearable. However, simple metrics like […]
Approximating Pareto Frontiers in Stochastic Multi-Objective Optimization via Hashing and Randomization
arXiv:2604.01098v1 Announce Type: cross Abstract: Stochastic Multi-Objective Optimization (SMOO) is critical for decision-making trading off multiple potentially conflicting objectives in uncertain environments. SMOO aims at identifying the Pareto frontier, which contains all mutually non-dominating decisions. The problem is highly intractable due to the embedded probabilistic inference, such as computing the marginal, posterior probabilities, or expectations. […]
Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
arXiv:2604.01170v1 Announce Type: cross Abstract: While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs. These inefficiencies can be attributed to the miscalibration of post-trained language models, and the lack of calibration in popular sampling techniques. Here, we present Online Reasoning Calibration (ORCA), a framework […]
The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline
arXiv:2604.01215v1 Announce Type: cross Abstract: AI weather prediction has advanced rapidly, yet no unified mathematical framework explains what determines forecast skill. Existing theory addresses specific architectural choices rather than the learning pipeline as a whole, while operational evidence from 2023-2026 demonstrates that training methodology, loss function design, and data diversity matter at least as much […]
LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning
arXiv:2506.13841v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs), particularly those enhanced through reinforced post-training, have demonstrated impressive reasoning capabilities, as exemplified by models such as OpenAI o1 and DeepSeek-R1. However, these capabilities are predominantly benchmarked on domains like mathematical problem solving and code generation, leaving open the question of whether such […]
Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming
arXiv:2510.18314v2 Announce Type: replace Abstract: As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security risks. However, relevant studies on web agent attacks remain limited. Existing red-teaming approaches mainly rely on manually crafted attack strategies or static models trained offline. Such methods fail to capture the […]
Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents
arXiv:2602.22413v2 Announce Type: replace Abstract: We investigate the collective accuracy of heterogeneous agents who learn to estimate their own reliability over time and selectively abstain from voting. While classical epistemic voting results, such as the textitCondorcet Jury Theorem (CJT), assume fixed participation, real-world aggregation often benefits from allowing agents to say “I don’t know.” We […]
But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors
arXiv:2505.17760v3 Announce Type: replace-cross Abstract: LLM-as-a-judge is widely used as a scalable substitute for human evaluation, yet current approaches rely on black-box access and struggle to detect subtle dishonesty, such as sycophancy and manipulation. We introduce Judge Using Safety-Steered Alternatives (JUSSA), a framework that leverages a model’s internal representations to optimize an honesty-promoting steering vector […]
Binned semiparametric Bayesian networks for efficient kernel density estimation
arXiv:2506.21997v3 Announce Type: replace-cross Abstract: This paper introduces a new type of probabilistic semiparametric model that takes advantage of data binning to reduce the computational cost of kernel density estimation in nonparametric distributions. Two new conditional probability distributions are developed for the new binned semiparametric Bayesian networks, the sparse binned kernel density estimation and the […]