arXiv:2506.04704v4 Announce Type: replace-cross Abstract: Despite emerging efforts to enhance the safety of Vision-Language Models (VLMs), current approaches face two main shortcomings. 1) Existing safety-tuning datasets and benchmarks only partially consider how image-text interactions can yield harmful content, often overlooking contextually unsafe outcomes from seemingly benign pairs. This narrow coverage leaves VLMs vulnerable to jailbreak […]
NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System
arXiv:2508.00709v2 Announce Type: replace-cross Abstract: Legal Judgment Prediction (LJP) has emerged as a key area in AI for law, aiming to automate judicial outcome forecasting and enhance interpretability in legal reasoning. While previous approaches in the Indian context have relied on internal case content such as facts, issues, and reasoning, they often overlook a core […]
Comparing Computational Pathology Foundation Models using Representational Similarity Analysis
arXiv:2509.15482v2 Announce Type: replace-cross Abstract: Foundation models are increasingly developed in computational pathology (CPath) given their promise in facilitating many downstream tasks. While recent studies have evaluated task performance across models, less is known about the structure and variability of their learned representations. Here, we systematically analyze the representational spaces of six CPath foundation models […]
Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
arXiv:2510.13865v4 Announce Type: replace-cross Abstract: We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant semantic information in high-frequency components while storing domain-specific biases in low-frequency components of deep features. By […]
Artificial Intelligence in Elementary STEM Education: A Systematic Review of Current Applications and Future Challenges
arXiv:2511.00105v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is transforming elementary STEM education, yet evidence remains fragmented. This systematic review synthesizes 258 studies (2020-2025) examining AI applications across eight categories: intelligent tutoring systems (45% of studies), learning analytics (18%), automated assessment (12%), computer vision (8%), educational robotics (7%), multimodal sensing (6%), AI-enhanced extended reality (XR) […]
Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video
arXiv:2511.03227v2 Announce Type: replace-cross Abstract: We present a node-based storytelling system for multimodal content generation. The system represents stories as graphs of nodes that can be expanded, edited, and iteratively refined through direct user edits and natural-language prompts. Each node can integrate text, images, audio, and video, allowing creators to compose multimodal narratives. A task […]
Differentially Private In-Context Learning with Nearest Neighbor Search
arXiv:2511.04332v1 Announce Type: cross Abstract: Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approaches overlook a critical component of modern large language model (LLM) pipelines: the similarity search used to retrieve relevant context data. In this work, we introduce a […]
On the Equivalence of Regression and Classification
arXiv:2511.04422v1 Announce Type: cross Abstract: A formal link between regression and classification has been tenuous. Even though the margin maximization term $|w|$ is used in support vector regression, it has at best been justified as a regularizer. We show that a regression problem with $M$ samples lying on a hyperplane has a one-to-one equivalence with […]
Fitting Reinforcement Learning Model to Behavioral Data under Bandits
arXiv:2511.04454v1 Announce Type: cross Abstract: We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years for characterizing human and animal decision making behavior. We provide a generic mathematical optimization problem formulation for the fitting problem […]
Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
arXiv:2511.04485v1 Announce Type: cross Abstract: Parameter-efficient training, based on low-rank optimization, has become a highly successful tool for fine-tuning large deep-learning models. However, these methods fail at low-rank pre-training tasks where maintaining the low-rank structure and the objective remains a challenging task. We propose the Quadratic Reweighted Rank Regularizer dubbed Q3R, which leads to a […]