AI Research Papers — Page 83

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

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

Notableresearch

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

May 12, 2026arXiv codeYuxiao Yang +2

Notableresearch

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

May 12, 2026arXiv codeXiao Cao +5

Notableresearch

Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring

May 12, 2026arXiv codeJamshid Mozafari +2

MajorresearchMeta

A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles

May 12, 2026arXiv codeMichela Lorandi +1

Notableresearch

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory

May 12, 2026arXiv codeHari K. Prakash +1

Notableresearch

Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning

May 12, 2026arXiv codeBrian P. Powell +5

Notableresearch

SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation

May 12, 2026arXiv codeLuke James Miller +1

Notableresearch

Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning

May 12, 2026arXiv codeHannes Büchi +3

Notableresearch

Scalable Token-Level Hallucination Detection in Large Language Models

May 12, 2026arXiv codeRui Min +4

Notableresearch

Pretraining Exposure Explains Popularity Judgments in Large Language Models

May 12, 2026arXiv codeJamshid Mozafari +2

Notableresearch

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training

May 12, 2026arXiv codeRasool Fakoor +3

Notableresearch

Discrete Flow Matching for Offline-to-Online Reinforcement Learning

May 12, 2026arXiv codeFairoz Nower Khan +2

Notableresearch

Fast Image Super-Resolution via Consistency Rectified Flow

May 12, 2026arXiv codeJiaqi Xu +5

Majorresearch

ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

May 12, 2026arXiv codeWei Liu +5

Notableresearch

Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts

May 12, 2026arXiv codeMatthew Beddows +2

Notableresearch

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

May 12, 2026arXiv codeYanting Miao +5

Notableresearch

Context Convergence Improves Answering Inferential Questions

May 12, 2026arXiv codeJamshid Mozafari +2

MajorresearchGoogle DeepMind

Classifier Context Rot: Monitor Performance Degrades with Context Length

May 12, 2026arXiv codeSam Martin +1

Notableresearch

QAP-Router: Tackling Qubit Routing as Dynamic Quadratic Assignment with Reinforcement Learning

May 12, 2026arXiv codeKien X. Nguyen +3

Notableresearch

A Family of Quaternion-Valued Differential Evolution Algorithms for Numerical Function Optimization

May 12, 2026arXiv codeGerardo Altamirano-Gomez +2

Notableresearch

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering

May 12, 2026arXiv codeRezarta Islamaj +5

NotableresearchHugging Face

Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation

May 12, 2026arXiv codeMichela Lorandi +1

Notableresearch

A categorical error sensitivity index (ISEC): A preventive ordinal decision-support measure for irrecoverable errors in manual data entry systems

May 12, 2026arXiv codeRicardo Raúl Palma +2

Notableresearch

Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging

May 12, 2026arXiv codeMd. Robiul Islam Niloy

Notableresearch

VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference

May 12, 2026arXiv codeHao Zhu +5

Notableresearch

Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering

May 12, 2026arXiv codeRezarta Islamaj +5

Notableresearch

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender

May 12, 2026arXiv codeLeonor Veloso +1

Notableresearch

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

May 12, 2026arXiv codeTruong Nguyen +5

Notableresearch

What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty

May 12, 2026arXiv codeJonas Mayer Martins +3

Majorresearch

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

May 12, 2026arXiv codeSae Furukawa +1