AI Research Papers — Page 65

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

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

Notableresearch

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models

May 21, 2026arXiv codePiotr Kubaty +5

Notableresearch

Swift Sampling: Selecting Temporal Surprises via Taylor Series

May 21, 2026arXiv codeDahye Kim +5

Notableresearch

Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment

May 21, 2026arXiv codeJanek Haberer +2

Majorresearch

Self-Policy Distillation via Capability-Selective Subspace Projection

May 21, 2026arXiv codeGuangya Hao +4

Notableresearch

From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

May 21, 2026arXiv codeBing Hu +5

MajorresearchOpenAI

OpenAI shifts the boundary of automated reasoning with a "milestone in AI mathematics" that experts are now unpacking

May 21, 2026

NotableresearchHugging Face

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

May 21, 2026arXiv codeJavad Rajabi +4

Notableresearch

Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora

May 21, 2026arXiv codeMaciej Skorski

Notableresearch

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

May 21, 2026arXiv codeZhenyu Lu +5

Majorresearch

Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs

May 21, 2026arXiv codeShanshan Wang +5

Notableresearch

Whose Voice Counts? Mapping Stakeholder Perspectives on AI Through Public Submissions to the U.S. Government

May 21, 2026arXiv codeAlina Karakanta +5

Majorresearch

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

May 21, 2026arXiv codePiercosma Bisconti +5

Notableresearch

More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

May 21, 2026arXiv codeVíctor Yeste +1

Notableresearch

The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution

May 21, 2026arXiv codeErjian Zhang +3

Notableresearch

Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework

May 21, 2026arXiv codeShourov Joarder +4

Notableresearch

Chinese sensorimotor and embodiment norms for 3,000 lexicalized concepts

May 21, 2026arXiv codeJing Chen +4

Notableresearch

Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents

May 21, 2026arXiv codeAsaf Yehudai +2

NotableresearchUiPath

A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models

May 21, 2026arXiv codeJiayi Fu +1

Notableresearch

Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion

May 21, 2026arXiv codeMeimingwei Li +3

Notableresearch

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance

May 21, 2026arXiv codeYuchun Fan +5

Notableresearch

SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations

May 21, 2026arXiv codeShuaiqi Wang +3

Notableresearch

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

May 21, 2026arXiv codeYevhen Kostiuk +1

Notableresearch

Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning

May 21, 2026arXiv codeYejin Cho +1

Notableresearch

SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation

May 21, 2026arXiv codeXiaolong Zhou +5

Notableresearch

Quantum Genetic Optimization for Negative Selection Algorithms in Anomaly Detection

May 21, 2026arXiv codeGiancarlo P. Gamberi +1

Notableresearch

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning

May 21, 2026arXiv codeZihan Liang +5

Notableresearch

Reflecti-Mate: A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinking

May 21, 2026arXiv codeMorita Tarvirdians +4

Notableresearch

BeLink: Biomedical Entity Linking Meets Generative Re-Ranking

May 21, 2026arXiv codeDarya Shlyk +2

Notableresearch

Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

May 21, 2026arXiv codeNils Leutenegger

Notableresearch

Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions

May 21, 2026arXiv codeGabriel Kronberger +4