arXiv:2603.14107v1 Announce Type: cross Abstract: Climate-vulnerable road networks require a paradigm shift from reactive, fix-on-failure repairs to predictive, decision-ready maintenance. This paper introduces ST-ResGAT, a novel Spatio-Temporal Residual Graph Attention Network that fuses residual graph-attention encoding with GRU temporal aggregation to forecast pavement deterioration. Engineered for resource-constrained deployment, the framework translates continuous Pavement Condition Index […]
Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing
arXiv:2603.09205v2 Announce Type: replace-cross Abstract: Large language models are routinely deployed on text that varies widely in emotional tone, yet their reasoning behavior is typically evaluated without accounting for emotion as a source of representational variation. Prior work has largely treated emotion as a prediction target, for example in sentiment analysis or emotion classification. In […]
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
arXiv:2603.14222v1 Announce Type: cross Abstract: Contrastive pretraining models such as CLIP and CLAP underpin many vision-language and audio-language systems, yet their reliance on web-scale data raises growing concerns about memorizing Personally Identifiable Information (PII). Auditing such models via membership inference is challenging in practice: shadow-model MIAs are computationally prohibitive for large multimodal backbones, and existing […]
A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study
arXiv:2603.14600v1 Announce Type: cross Abstract: Reinforcement learning algorithms have been widely used in dynamic and control systems. However, interpreting their internal learning behavior remains a challenge. In the authors’ previous work, a critic match loss landscape visualization method was proposed to study critic training. This study extends that method into a framework which provides a […]
AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models
arXiv:2603.14342v1 Announce Type: cross Abstract: Agricultural multimodal reasoning requires robust spatial understanding across varying scales, from ground-level close-ups to top-down UAV and satellite imagery. Existing Multi-modal Large Language Models (MLLMs) suffer from a significant “terrestrial-centric” bias, causing scale confusion and logic drift during complex agricultural planning. To address this, we introduce the first large-scale AgroOmni […]
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
arXiv:2603.08309v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on simple foreground-background masks, which fail to capture the fine-grained semantic concepts that define an object (e.g., “long beak” and “wings” for […]
Geometric and Topological Deep Learning for Predicting Thermo-mechanical Performance in Cold Spray Deposition Process Modeling
arXiv:2603.14478v1 Announce Type: cross Abstract: This study presents a geometric deep learning framework for predicting cold spray particle impact responses using finite element simulation data. A parametric dataset was generated through automated Abaqus simulations spanning a systematic range of particle velocity, particle temperature, and friction coefficient, yielding five output targets including maximum equivalent plastic strain, […]
FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference
arXiv:2603.14591v1 Announce Type: cross Abstract: Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabulary sizes continue to grow rapidly, making the classification head a critical bottleneck that accounts for up to 60% of model parameters, and 50% of inference compute. We introduce […]
Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
arXiv:2603.13341v1 Announce Type: cross Abstract: Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown promising results. Current works in traditional visual models suggest that improving visual discriminability enhances performance. However, in VLM-based SF-CDFSL […]
OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions
arXiv:2603.07431v2 Announce Type: replace-cross Abstract: Transformer architectures excel at sequential modeling yet remain fundamentally limited by correlational learning – they capture spurious associations induced by latent confounders rather than invariant causal mechanisms. We identify this as an epistemological challenge: standard Transformers conflate static background factors (intrinsic identity, style, context) with dynamic causal flows (state evolution, […]
BrainCast: A Spatio-Temporal Forecasting Model for Whole-Brain fMRI Time Series Prediction
arXiv:2603.13361v1 Announce Type: cross Abstract: Functional magnetic resonance imaging (fMRI) enables noninvasive investigation of brain function, while short clinical scan durations, arising from human and non-human factors, usually lead to reduced data quality and limited statistical power for neuroimaging research. In this paper, we propose BrainCast, a novel spatio-temporal forecasting framework specifically tailored for whole-brain […]
Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
arXiv:2603.14589v1 Announce Type: cross Abstract: This work extends an established critic match loss landscape visualization method from online to off-policy reinforcement learning (RL), aiming to reveal the optimization geometry behind critic learning. Off-policy RL differs from stepwise online actor-critic learning in its replay-based data flow and target computation. Based on these two structural differences, the […]