10,434 articles

📰 AI News

10,434 articles · Updated every 3 hours

All ⚡ AI Lessons (6067) ArXiv cs.AIForbes InnovationOpenAI NewsDev.to AIHugging Face BlogHackernoon
ArXiv cs.AI 📄 Paper 23h ago
Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
arXiv:2510.13909v2 Announce Type: replace-cross Abstract: Inductive Knowledge Graph Reasoning (KGR) aims to discover facts in open-domain KGs containing unknown
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
arXiv:2510.14628v2 Announce Type: replace-cross Abstract: Recent advances in Text-To-Speech (TTS) synthesis have achieved near-human speech quality in neutral s
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Fairness Evaluation and Inference Level Mitigation in LLMs
arXiv:2510.18914v3 Announce Type: replace-cross Abstract: Large language models often display undesirable behaviors embedded in their internal representations,
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
arXiv:2510.23409v3 Announce Type: replace-cross Abstract: Data valuation has become central in the era of data-centric AI. It drives efficient training pipeline
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors
arXiv:2510.25241v2 Announce Type: replace-cross Abstract: Whole-body humanoid motion represents a fundamental challenge in robotics, requiring balance, coordina
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Routing-Based Continual Learning for Multimodal Large Language Models
arXiv:2511.01831v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catast
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Cortex AISQL: A Production SQL Engine for Unstructured Data
arXiv:2511.07663v3 Announce Type: replace-cross Abstract: Snowflake's Cortex AISQL is a production SQL engine that integrates native semantic operations directl
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving
arXiv:2512.10785v2 Announce Type: replace-cross Abstract: Generative AI offers new opportunities for individualized and adaptive learning, e.g., through large l
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
arXiv:2512.16251v4 Announce Type: replace-cross Abstract: We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst con
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Automatic Replication of LLM Mistakes in Medical Conversations
arXiv:2512.20983v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly evaluated in clinical settings using multi-dimensional r
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
arXiv:2512.23994v2 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
arXiv:2601.02978v2 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of in
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
arXiv:2601.03054v4 Announce Type: replace-cross Abstract: Recent research on medical MLLMs has gradually shifted its focus from image-level understanding to fin
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
arXiv:2601.05905v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Can We Predict Before Executing Machine Learning Agents?
arXiv:2601.05930v2 Announce Type: replace-cross Abstract: Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrain
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs
arXiv:2601.09365v2 Announce Type: replace-cross Abstract: Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology
arXiv:2601.10073v2 Announce Type: replace-cross Abstract: We introduce ReaMIL (Reasoning- and Evidence-Aware MIL), a multiple instance learning approach for who
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching
arXiv:2601.11652v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
arXiv:2601.16211v2 Announce Type: replace-cross Abstract: Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combination
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model
arXiv:2601.22581v2 Announce Type: replace-cross Abstract: Although cross-domain few-shot learning (CDFSL) for hyper-spectral image (HSI) classification has attr
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
R3G: A Reasoning--Retrieval--Reranking Framework for Vision-Centric Answer Generation
arXiv:2602.00104v2 Announce Type: replace-cross Abstract: Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrat
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities
arXiv:2602.00185v2 Announce Type: replace-cross Abstract: The integration of large language models (LLMs) into materials science offers a transformative opportu
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration
arXiv:2602.00913v3 Announce Type: replace-cross Abstract: Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether
Read paper → + Playlist
ArXiv cs.AI 📄 Paper 23h ago
Incident-Guided Spatiotemporal Traffic Forecasting
arXiv:2602.02528v2 Announce Type: replace-cross Abstract: Recent years have witnessed the rapid development of deep-learning-based, graph-neural-network-based f
Read paper → + Playlist