AI Research Papers — Page 56

AI News →Multi-source stories →Browse by company →

Archive, newest first. Filter by topic, impact and company →

Notableresearch

Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models

May 27, 2026arXiv codeJiawei Zhang +4

Notableresearch

Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study

May 27, 2026arXiv codeIrune Zubiaga +2

Notableresearch

Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI

May 27, 2026arXiv codeAisha Aijaz +3

Notableresearch

Understanding Generalization and Forgetting in In-Context Continual Learning

May 27, 2026arXiv codeGuangyu Li +2

Notableresearch

Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations

May 27, 2026arXiv codeYeachan Park +3

Notableresearch

A Fresh Look at Lamarckian Evolution and the Baldwin Effect

May 27, 2026arXiv codeInès Benito +2

Notableresearch

The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic

May 27, 2026arXiv codeDominika Agnieszka Długosz +2

Notableresearch

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

May 27, 2026arXiv codeChusen Li +3

Notableresearch

Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?

May 27, 2026arXiv codeThierry Judge +5

Notableresearch

Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images

May 27, 2026arXiv codeJoséphine Raugel +5

NotableresearchHugging Face

OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning

May 27, 2026arXiv codeYunyang Ge +5

Notableresearch

Latent-Conditioned Parameterized Quantum Circuits as Universal Approximators for Distributions over Quantum States

May 27, 2026arXiv codeQuoc Hoan Tran +3

NotableresearchOpenAI

History-aware adaptive reduced-order models via incremental singular value decomposition

May 27, 2026arXiv codeAmirpasha Hedayat +4

Notableresearch

Optimal ridge regularization revisited

May 27, 2026arXiv codeJack Timmermans +1

Notableresearch

Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective

May 27, 2026arXiv codeMingjie Hu +2

Notableresearch

Sense Representations Are Inducible Interfaces

May 27, 2026arXiv codeJan Christian Blaise Cruz +1

Notableresearch

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection

May 27, 2026arXiv codeVijeta Deshpande +4

Notableresearch

Applications of temporal graph learning for predicting the dynamics of biological systems

May 27, 2026arXiv codeManuel Dileo +1

NotableresearchGoogle DeepMind

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing

May 27, 2026arXiv codeLi Lei +3

Notableresearch

MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution

May 27, 2026arXiv codeYanqiu Zhao +5

Majorresearch

GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction

May 27, 2026arXiv codeJinze Gu +3

Notableresearch

GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study

May 27, 2026arXiv codeGaspard Michel +4

Majorresearch

The Attentional White Bear Effect in Transformer Language Models

May 27, 2026arXiv codeRebecca Ramnauth +1

Majorresearch

EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection

May 27, 2026arXiv codeXinyu Zhao +3

Majorresearch

Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents

May 27, 2026arXiv codeZheng Wu +5

Notableresearch

A Multiscale Kinetic Framework for Image Segmentation: From Particle Systems to Continuum Models

May 27, 2026arXiv codeHoracio Tettamanti +2

Notableresearch

Measuring Form and Function in Language Models

May 27, 2026arXiv codeHéctor Javier Vázquez Martínez +1

Notableresearch

Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization

May 27, 2026arXiv codeZhuohan Liu +3

Notableresearch

JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models

May 27, 2026arXiv codeJiachen Qian

Notableresearch

Internally Referenced Low-Light Enhancement

May 27, 2026arXiv codePeiyuan He +4