AI Research Papers — Page 81

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

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

Notableresearch

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning

May 13, 2026arXiv codeHee Suk Yoon +5

Notableresearch

LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking

May 13, 2026arXiv codeAdam Remaki +2

Notableresearch

Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers

May 13, 2026arXiv codeSamuel Schapiro +3

Notableresearch

The Geno-Synthetic Algorithm: Type-Factored Coevolutionary Optimization for Heterogeneous Genotypes and Assembled Phenotypes

May 13, 2026arXiv codeAlex Bogdan

Notableresearch

Ghost of long-extinct ancestor lives on in people today

May 13, 2026

Notableresearch

TRUST-TAEA: A trustworthiness-guided two-archive evolutionary algorithm with variable-grouping sparse search for large-scale multi-objective optimization

May 13, 2026arXiv codeJunYi Cui

Notableresearch

Fluffy ice could imperil spacecraft landings on ocean moons

May 13, 2026

Notableresearch

Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation

May 13, 2026arXiv codeJohnson Zhou +5

Notableresearch

FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping

May 13, 2026arXiv codeJongmin Choi +1

Notableresearch

Boy’s brain tumor tied to gene therapy

May 13, 2026

Notableresearch

Gotcha! Odd language mistakes may help identify fake papers

May 13, 2026

Notableresearch

A generative artificial intelligence approach for peptide antibiotic optimization

May 13, 2026

Majorresearch

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

May 12, 2026arXiv codeHaiwen Diao +5

Notableresearch

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

May 12, 2026arXiv codeMiaosen Zhang +5

Majorresearch

EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

May 12, 2026arXiv codeChristen Millerdurai +5

Notableresearch

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

May 12, 2026arXiv codeYihao Meng +5

Notableresearch

From Web to Pixels: Bringing Agentic Search into Visual Perception

May 12, 2026arXiv codeBokang Yang +5

Notableresearch

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

May 12, 2026arXiv codeRunhui Huang +4

Notableresearch

Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

May 12, 2026arXiv codeJiahe Li +5

Notableresearch

LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues

May 12, 2026arXiv codeDi Wu +5

Notableresearch

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

May 12, 2026arXiv codeKexuan Shi +5

NotableresearchHugging Face

Elastic Attention Cores for Scalable Vision Transformers

May 12, 2026arXiv codeAlan Z. Song +5

NotableresearchIBM

Task-Adaptive Embedding Refinement via Test-time LLM Guidance

May 12, 2026arXiv codeAriel Gera +4

Majorresearch

Learning, Fast and Slow: Towards LLMs That Adapt Continually

May 12, 2026arXiv codeRishabh Tiwari +5

Notableresearch

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training

May 12, 2026arXiv codeYuanda Xu +5

MajorresearchUiPath

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

May 12, 2026arXiv codeXuhao Hu +5

Notableresearch

OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation

May 12, 2026arXiv codeGuohui Zhang +5

Notableresearch

MEME: Multi-entity & Evolving Memory Evaluation

May 12, 2026arXiv codeSeokwon Jung +4

Notableresearch

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts

May 12, 2026arXiv codeSagi Ahrac +2

Notableresearch

Reward Hacking in Rubric-Based Reinforcement Learning

May 12, 2026arXiv codeAnas Mahmoud +5