📰 AI News

8,196 articles · Updated every 3 hours

arXiv:2603.24828v1 Announce Type: cross Abstract: Clinical decisions are high-stakes and require explicit justification, making model interpretability essential

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

arXiv:2603.24844v1 Announce Type: cross Abstract: Given a question, a language model (LM) implicitly encodes a distribution over possible answers. In practice,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

NeuroVLM-Bench: Evaluation of Vision-Enabled Large Language Models for Clinical Reasoning in Neurological Disorders

arXiv:2603.24846v1 Announce Type: cross Abstract: Recent advances in multimodal large language models enable new possibilities for image-based decision support.

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Gaze patterns predict preference and confidence in pairwise AI image evaluation

arXiv:2603.24849v1 Announce Type: cross Abstract: Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference O

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective

arXiv:2603.24857v1 Announce Type: cross Abstract: As machine learning (ML) systems expand in both scale and functionality, the security landscape has become inc

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes

arXiv:2603.24877v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) tools can now help people perform complex data science tasks regardles

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware

arXiv:2603.24891v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer inherent advantages for low-power inference through sparse, event-driven

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

LogSigma at SemEval-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis

arXiv:2603.24896v1 Announce Type: cross Abstract: This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Sovereign AI at the Front Door of Care: A Physically Unidirectional Architecture for Secure Clinical Intelligence

arXiv:2603.24898v1 Announce Type: cross Abstract: We present a Sovereign AI architecture for clinical triage in which all inference is performed on-device and i

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Integrated Multi-Drone Task Allocation, Sequencing, and Optimal Trajectory Generation in Obstacle-Rich 3D Environments

arXiv:2603.24908v1 Announce Type: cross Abstract: Coordinating teams of aerial robots in cluttered three-dimensional (3D) environments requires a principled int

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Shaping the Future of Mathematics in the Age of AI

arXiv:2603.24914v1 Announce Type: cross Abstract: Artificial intelligence is transforming mathematics at a speed and scale that demand active engagement from th

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

CVA: Context-aware Video-text Alignment for Video Temporal Grounding

arXiv:2603.24934v1 Announce Type: cross Abstract: We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in v

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Driven Optimization

arXiv:2603.24936v1 Announce Type: cross Abstract: Human trajectory forecasting is important for intelligent multimedia systems operating in visually complex env

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system

arXiv:2603.24940v1 Announce Type: cross Abstract: This paper introduces the design and development of a framework that integrates a large language model (LLM) w

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Toward domain-specific machine translation and quality estimation systems

arXiv:2603.24955v1 Announce Type: cross Abstract: Machine Translation (MT) and Quality Estimation (QE) perform well in general domains but degrade under domain

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Self-Corrected Image Generation with Explainable Latent Rewards

arXiv:2603.24965v1 Announce Type: cross Abstract: Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challe

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Subject-Specific Low-Field MRI Synthesis via a Neural Operator

arXiv:2603.24968v1 Announce Type: cross Abstract: Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but generally has low

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators

arXiv:2603.24986v1 Announce Type: cross Abstract: Large language model based health agents are increasingly used by health consumers and clinicians to interpret

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model

arXiv:2603.24989v1 Announce Type: cross Abstract: Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autono

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients

arXiv:2603.24999v1 Announce Type: cross Abstract: The validity of assessments, from large-scale AI benchmarks to human classrooms, depends on the quality of ind

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning

arXiv:2603.25006v1 Announce Type: cross Abstract: Early detection of rice leaf diseases is critical, as rice is a staple crop supporting a substantial share of

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 1w ago

Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

arXiv:2603.25008v1 Announce Type: cross Abstract: This paper presents Few TensoRF, a 3D reconstruction framework that combines TensorRF's efficient tensor based

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models

arXiv:2603.25015v1 Announce Type: cross Abstract: System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but o

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1w ago

Closing the Confidence-Faithfulness Gap in Large Language Models

arXiv:2603.25052v1 Announce Type: cross Abstract: Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual a