AI Research Papers — Page 79

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

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

Notableresearch

Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling

May 13, 2026arXiv codeDeepak Pandita +3

Notableresearch

VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence

May 13, 2026arXiv codeGuney Tombak +2

Notableresearch

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed

May 13, 2026arXiv codeZhongtao Wang +5

Notableresearch

An LLM-Based System for Argument Reconstruction

May 13, 2026arXiv codePaulo Pirozelli +3

Majorresearch

Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations

May 13, 2026arXiv codeZhonghao Li +2

Notableresearch

ENSEMBITS: an alphabet of protein conformational ensembles

May 13, 2026arXiv codeKaiwen Shi +1

Notableresearch

Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs

May 13, 2026arXiv codeEszter Varga-Umbrich +5

Notableresearch

Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data

May 13, 2026arXiv codeChuanchuan Sun +4

Notableresearch

Amplification to Synthesis: A Comparative Analysis of Cognitive Operations Before and After Generative AI

May 13, 2026arXiv codeLiz Cho +1

Notableresearch

Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers

May 13, 2026arXiv codeVictor Norgren

NotableresearchUiPath

LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration

May 13, 2026arXiv codeJonathan A. Diller +3

Notableresearch

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

May 13, 2026arXiv codeMind Lab +5

Notableresearch

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs

May 13, 2026arXiv codeJiahui Niu +5

Majorresearch

RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

May 13, 2026arXiv codeHarold Haodong Chen +4

Notableresearch

(How) Do Large Language Models Understand High-Level Message Sequence Charts?

May 13, 2026arXiv codeMohammad Reza Mousavi

Notableresearch

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry

May 13, 2026arXiv codeTyler Alvarez +1

Notableresearch

Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching

May 13, 2026arXiv codeAbdalrahman Wael

Notableresearch

High-Rate Quantized Matrix Multiplication II

May 13, 2026arXiv codeOr Ordentlich +1

Majorresearch

VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense

May 13, 2026arXiv codeJascha Wanger

Majorresearch

Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations

May 13, 2026arXiv codePhillip Si +5

NotableresearchMeta

Fast and effective algorithms for fair clustering at scale

May 13, 2026arXiv codeClaudio Mantuano +2

Notableresearch

Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception

May 13, 2026arXiv codeArka Bhowmick +3

NotableresearchUiPath

Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein

May 13, 2026arXiv codeAshkan Shahbazi +3

Notableresearch

Weakly-Supervised Spatiotemporal Anomaly Detection

May 13, 2026arXiv codeUrvi Gianchandani +2

Notableresearch

Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration

May 13, 2026arXiv codeFeiyu Tan +3

Notableresearch

GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction

May 13, 2026arXiv codeYifan Duan +4

Notableresearch

LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction

May 13, 2026arXiv codeChristina Kassab +4

Notableresearch

Learning POMDP World Models from Observations with Language-Model Priors

May 13, 2026arXiv codeValentin Six +5

Notableresearch

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

May 13, 2026arXiv codeTrung Nguyen Quang +5

Notableresearch

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

May 13, 2026arXiv codeZedong Liu +5