⚡ AI-Lesson Articles

5,434 articles · Updated every 3 hours · View all news

arXiv:2603.22303v1 Announce Type: cross Abstract: Hallucinations in large language models (LLMs) remain a central obstacle to trustworthy deployment, motivating

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

CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News

arXiv:2603.22305v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks inc

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

UniFluids: Unified Neural Operator Learning with Conditional Flow-matching

arXiv:2603.22309v1 Announce Type: cross Abstract: Partial differential equation (PDE) simulation holds extensive significance in scientific research. Currently,

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

A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection

arXiv:2603.22313v1 Announce Type: cross Abstract: The increasing global aging population has intensified the demand for reliable health monitoring systems, part

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

Enhancing AI-Based Tropical Cyclone Track and Intensity Forecasting via Systematic Bias Correction

arXiv:2603.22314v1 Announce Type: cross Abstract: Tropical cyclones (TCs) pose severe threats to life, infrastructure, and economies in tropical and subtropical

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

Emergency Preemption Without Online Exploration: A Decision Transformer Approach

arXiv:2603.22315v1 Announce Type: cross Abstract: Emergency vehicle (EV) response time is a critical determinant of survival outcomes, yet deployed signal preem

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

ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography

arXiv:2603.22316v1 Announce Type: cross Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordinati

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

Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning

arXiv:2603.22317v1 Announce Type: cross Abstract: Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accur

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

Sparsely-Supervised Data Assimilation via Physics-Informed Schr\"odinger Bridge

arXiv:2603.22319v1 Announce Type: cross Abstract: Data assimilation (DA) for systems governed by partial differential equations (PDE) aims to reconstruct full s

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

From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs

arXiv:2603.22321v1 Announce Type: cross Abstract: The recent advancements introduced by Large Language Models (LLMs) have transformed how Artificial Intelligenc

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

AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations

arXiv:2603.22322v1 Announce Type: cross Abstract: Machine learning systems deployed in medical devices require governance frameworks that ensure safety while en

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

A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life

arXiv:2603.22323v1 Announce Type: cross Abstract: Accurately predicting the state-of-health (SOH) and remaining useful life (RUL) of lithium-ion batteries is cr

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

DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression

arXiv:2603.22324v1 Announce Type: cross Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves t

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

Hybrid Associative Memories

arXiv:2603.22325v1 Announce Type: cross Abstract: Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain

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

A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance

arXiv:2603.22326v1 Announce Type: cross Abstract: Decision support systems are essential for maintaining grid stability in low-carbon power systems, such as win

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

AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI

arXiv:2603.22327v1 Announce Type: cross Abstract: Systematic literature reviews are essential for synthesizing scientific evidence but are costly, difficult to

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

Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression

arXiv:2603.22328v1 Announce Type: cross Abstract: Despite the strong predictive performance achieved by machine learning models across many application domains,

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

Trained Persistent Memory for Frozen Decoder-Only LLMs

arXiv:2603.22329v1 Announce Type: cross Abstract: Decoder-only language models are stateless: hidden representations are discarded after every forward pass and

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

Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models

arXiv:2603.22331v1 Announce Type: cross Abstract: Every wildfire prediction model deployed today shares a dangerous property: none of these methods provides for

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

Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms

arXiv:2603.22332v1 Announce Type: cross Abstract: Data imputation is a cornerstone technique for handling missing values in real-world datasets, which are often

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

Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation

arXiv:2603.22333v1 Announce Type: cross Abstract: State-space models (SSMs) offer efficient alternatives to attention with linear-time recurrence. Mamba2, a rec

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

Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation

arXiv:2603.22335v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned w

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

Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

arXiv:2603.22340v1 Announce Type: cross Abstract: Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet tra

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

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

arXiv:2603.22341v1 Announce Type: cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLM