AI Research Papers — Page 105

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

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

Notableresearch

A Toolkit for Detecting Spurious Correlations in Speech Datasets

Apr 29, 2026arXiv codeLara Gauder +5

Notableresearch

From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy

Apr 29, 2026arXiv codeSerhii Zabolotnii +2

Notableresearch

Differentially-Private Text Rewriting reshapes Linguistic Style

Apr 29, 2026arXiv codeStefan Arnold

Notableresearch

Evolutionary feature selection for spiking neural network pattern classifiers

Apr 29, 2026arXiv codeMichal Valko +2

MajorresearchDeepSeek

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models

Apr 29, 2026arXiv codeDongxin Guo +2

Notableresearch

SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data

Apr 29, 2026arXiv codeDianyu Liu +5

Notableresearch

When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

Apr 29, 2026arXiv codeZhimin Lin +5

Notableresearch

ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation

Apr 29, 2026arXiv codeSergej Stanovcic +2

Notableresearch

SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection

Apr 29, 2026arXiv codePaul Julius Kühn +3

Notableresearch

SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling

Apr 29, 2026arXiv codeEliya Naomi Aharon +5

Notableresearch

OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory

Apr 29, 2026arXiv codeJinze Li +5

Notableresearch

Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis

Apr 29, 2026arXiv codeJakob Fehle +3

Notableresearch

TDD Governance for Multi-Agent Code Generation via Prompt Engineering

Apr 29, 2026arXiv codeTarlan Hasanli +5

Notableresearch

Human-in-the-Loop Benchmarking of Heterogeneous LLMs for Automated Competency Assessment in Secondary Level Mathematics

Apr 29, 2026arXiv codeJatin Bhusal +3

Notableresearch

Translating Under Pressure: Domain-Aware LLMs for Crisis Communication

Apr 29, 2026arXiv codeAntonio Castaldo +4

Majorresearch

MappingEvolve: LLM-Driven Code Evolution for Technology Mapping

Apr 29, 2026arXiv codeRongliang Fu +3

Notableresearch

Star-Fusion: A Multi-modal Transformer Architecture for Discrete Celestial Orientation via Spherical Topology

Apr 29, 2026arXiv codeMay Hammad +1

Majorresearch

Multimodal LLMs are not all you need for Pediatric Speech Language Pathology

Apr 29, 2026arXiv codeDarren Fürst +2

Notableresearch

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models

Apr 29, 2026arXiv codeJinho Choo +5

Notableresearch

Battle over DNA within fertilized eggs may explain why some IVF procedures fail

Apr 29, 2026

Notableresearch

Text-Utilization for Encoder-dominated Speech Recognition Models

Apr 29, 2026arXiv codeAlbert Zeyer +3

Majorresearch

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

Apr 29, 2026arXiv codeYuan Xin +5

Notableresearch

Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain

Apr 29, 2026arXiv codeShang-Hsuan Chiang +3

Notableresearch

StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario

Apr 29, 2026arXiv codeMarcely Zanon Boito +5

Notableresearch

Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization

Apr 29, 2026arXiv codeYash Ganpat Sawant

Notableresearch

Naamah: A Large Scale Synthetic Sanskrit NER Corpus via DBpedia Seeding and LLM Generation

Apr 29, 2026arXiv codeAkhil Rajeev P +1

Notableresearch

EmoTransCap: Dataset and Pipeline for Emotion Transition-Aware Speech Captioning in Discourses

Apr 29, 2026arXiv codeShuhao Xu +5

Notableresearch

When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

Apr 29, 2026arXiv codeTianyu Liu +5