arXiv:2603.21359v1 Announce Type: cross Abstract: Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting […]
Cross-talk based multi-task learning for fault classification of machine system influenced by multiple variables
arXiv:2602.05146v2 Announce Type: replace-cross Abstract: Machine systems inherently generate signals in which fault conditions and various variables influence signals measured from machine system. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other variables. Herein, we leverage this through a multi-task learning (MTL) […]
Not All Latent Spaces Are Flat: Hyperbolic Concept Control
arXiv:2603.14093v2 Announce Type: replace-cross Abstract: As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce […]
Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
arXiv:2603.16065v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a framework for online policy refinement by adapting foundation VLMs into online reward generators. We develop a robust, scalable […]
Generalized Discrete Diffusion from Snapshots
arXiv:2603.21342v1 Announce Type: cross Abstract: We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on […]
BOxCrete: A Bayesian Optimization Open-Source AI Model for Concrete Strength Forecasting and Mix Optimization
arXiv:2603.21525v1 Announce Type: cross Abstract: Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets […]
Spatial Transcriptomics as Images for Large-Scale Pretraining
arXiv:2603.13432v3 Announce Type: replace-cross Abstract: Spatial Transcriptomics (ST) profiles thousands of gene expression values at discrete spots with precise coordinates on tissue sections, preserving spatial context essential for clinical and pathological studies. With rising sequencing throughput and advancing platforms, the expanding data volumes motivate large-scale ST pretraining. However, the fundamental unit for pretraining, i.e., what […]
Individual-based stochastic model with unbounded growth, birth and death rates: a tightness result
arXiv:2603.21634v1 Announce Type: cross Abstract: We study population dynamics through a general growth/degrowth-fragmentation process, with resource consumption and unbounded growth/degrowth, birth and death rates. Our model is structured in a positive trait called energy (which is a proxy for any biological parameter such as size, age, mass, protein quantity…), and the jump rates of the […]
COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding
arXiv:2603.21329v1 Announce Type: cross Abstract: Understanding human intent is a high-level cognitive challenge for Large Language Models (LLMs), requiring sophisticated reasoning over noisy, conflicting, and non-linear discourse. While LLMs excel at following individual instructions, their ability to distill Collective Intent – the process of extracting consensus, resolving contradictions, and inferring latent trends from multi-source public […]
PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation
arXiv:2603.13275v3 Announce Type: replace-cross Abstract: Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches-from machine learning (ML) to fine-tuned large language models (LLMs)-have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising […]
Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases
arXiv:2603.21935v1 Announce Type: cross Abstract: Quantitative disease severity scoring in medical imaging is costly, time-consuming, and subject to inter-reader variability. At the same time, clinical archives contain far more longitudinal imaging data than expert-annotated severity scores. Existing self-supervised methods typically ignore this chronological structure. We introduce ChronoCon, a contrastive learning approach that replaces label-based ranking […]
B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture
arXiv:2603.21326v1 Announce Type: cross Abstract: Jet flavor tagging plays an important role in precise Standard Model measurement enabling the extraction of mass dependence in jet-quark interaction and quark-gluon plasma (QGP) interactions. They also enable inferring the nature of particles produced in high-energy particle collisions that contain heavy quarks. The classification of bottom jets is vital […]