AI Research Papers — Page 74

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

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

Notableresearch

Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video

May 18, 2026arXiv codeArslan Artykov +3

Notableresearch

Post-Trained MoE Can Skip Half Experts via Self-Distillation

May 18, 2026arXiv codeXingtai Lv +5

Notableresearch

Leveraging Latent Visual Reasoning in Silence

May 18, 2026arXiv codeDongyao Zhu +5

Notableresearch

Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models

May 18, 2026arXiv codeAditya Tanna +5

NotableresearchServiceNow

Position: Weight Space Should Be a First-Class Generative AI Modality

May 18, 2026arXiv codeZhangyang Wang +2

Notableresearch

SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science

May 18, 2026arXiv codeNithin Somasekharan +5

Notableresearch

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)

May 18, 2026arXiv codeMichał Brzozowski +1

Majorresearch

Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection

May 18, 2026arXiv codeJuozas Dautartas +3

Notableresearch

Forecasting Downstream Performance of LLMs With Proxy Metrics

May 18, 2026arXiv codeArkil Patel +3

Notableresearch

AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning

May 18, 2026arXiv codePeilin Wu +5

MajorresearchServiceNow

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

May 18, 2026arXiv codeYubin Qu +5

NotableresearchNVIDIA

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

May 18, 2026

NotableresearchMeta

MA²P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion

May 18, 2026arXiv codeDingyi Zhang +4

Notableresearch

GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems

May 18, 2026arXiv codeMaximilian Reinhardt +2

Notableresearch

LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

May 18, 2026arXiv codeHyunji Lee +5

NotableresearchUiPath

Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences

May 18, 2026arXiv codeThomas Hikaru Clark +2

Notableresearch

Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data

May 18, 2026arXiv codeAriane Delrocq +3

Notableresearch

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

May 18, 2026arXiv codeMaciej Chrabąszcz +4

Notableresearch

STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics

May 18, 2026arXiv codeTingfeng Hui +5

Majorresearch

Continuous Diffusion Scales Competitively with Discrete Diffusion for Language

May 18, 2026arXiv codeZhihan Yang +5

Notableresearch

Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection

May 18, 2026arXiv codeHaochun Wang +5

Notableresearch

Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models

May 18, 2026arXiv codeSpyridon Mavromatis +3

Notableresearch

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning

May 18, 2026arXiv codeLi Wang +5

Notableresearch

Vector RAG vs LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research

May 18, 2026arXiv codeTheodore O. Cochran

Notableresearch

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

May 18, 2026arXiv codeSixu Chen +5

Notableresearch

From BERT to T5: A Study of Named Entity Recognition

May 18, 2026arXiv codeMei Jia

Notableresearch

When Fireflies Cluster; Enhancing Automatic Clustering via Centroid-Guided Firefly Optimization

May 18, 2026arXiv codeMKA Ariyaratne +3

Notableresearch

What is Holding Back Latent Visual Reasoning?

May 18, 2026arXiv codeAndré G. Viveiros +3

Notableresearch

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

May 18, 2026arXiv codeYuyao Wang +5

Notableresearch

Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization

May 18, 2026arXiv codeMeng Xiang +1