AI Research Papers — Page 87

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

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

Notableresearch

Joint sparse coding and temporal dynamics support context reconfiguration

May 11, 2026arXiv codeQianqian Shi +5

Notableresearch

Prospective Compression in Human Abstraction Learning

May 11, 2026arXiv codeLeonardo Hernandez Cano +5

Notableresearch

Frequency Matching in Spiking Neural Networks for mmWave Sensing

May 11, 2026arXiv codeDi Yu +5

Notableresearch

Re-thinking human–machine interaction and the governance of AI in the military domain

May 11, 2026

Notableresearch

Towards the explainability of protein language models

May 11, 2026

MajorresearchAnthropic

Researchers may have found a way to stop AI models from intentionally playing dumb during safety evaluations

May 10, 2026

NotableresearchHugging Face

"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"

May 9, 2026

NotableresearchHugging Face

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

May 8, 2026

NotableresearchHugging Face

EMO: Pretraining mixture of experts for emergent modularity

May 8, 2026

Notableresearch

Fiber optic cables can eavesdrop on nearby conversations

May 8, 2026

NotableresearchAMD

MedQA: Fine-Tuning a Clinical AI on AMD ROCm — No CUDA Required

May 8, 2026

Notableresearch

As researchers aim for universal AI disclosure guidelines, the devil is in the details

May 8, 2026

Notableresearch

ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation

May 7, 2026arXiv codeOmar El Khalifi +5

Notableresearch

UniPool: A Globally Shared Expert Pool for Mixture-of-Experts

May 7, 2026arXiv codeMinbin Huang +5

Notableresearch

BAMI: Training-Free Bias Mitigation in GUI Grounding

May 7, 2026arXiv codeBorui Zhang +5

Majorresearch

EMO: Pretraining Mixture of Experts for Emergent Modularity

May 7, 2026arXiv codeRyan Wang +2

Majorresearch

Verifier-Backed Hard Problem Generation for Mathematical Reasoning

May 7, 2026arXiv codeYuhang Lai +3

Notableresearch

Relit-LiVE: Relight Video by Jointly Learning Environment Video

May 7, 2026arXiv codeWeiqing Xiao +5

Notableresearch

Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML

May 7, 2026arXiv codeJai Moondra +3

Notableresearch

Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less

May 7, 2026arXiv codeYuxing Liu +2

Notableresearch

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels

May 7, 2026arXiv codeSushant Gautam +5

Majorresearch

AI Co-Mathematician: Accelerating Mathematicians with Agentic AI

May 7, 2026arXiv codeDaniel Zheng +5

Notableresearch

Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients

May 7, 2026arXiv codeMingwei Xu +1

Majorresearch

Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval

May 7, 2026arXiv codeZeyu Yang +3

Notableresearch

Inductive Venn-Abers and related regressors

May 7, 2026arXiv codeIvan Petej +1

Notableresearch

Edge-specific signal propagation on mature chromophore-region 3D mechanism graphs for fluorescent protein quantum-yield prediction

May 7, 2026arXiv codeYuchen Xiong +2

Notableresearch

Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study

May 7, 2026arXiv codeHao Dong +5

Majorresearch

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

May 7, 2026arXiv codeXiangyuan Xue +5

Notableresearch

Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models

May 7, 2026arXiv codeRonaldo Canizales +3

Notableresearch

GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation

May 7, 2026arXiv codeZiyu Zhai +3