AI Research Papers — Page 84

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

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

Notableresearch

PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents

May 12, 2026arXiv codeJingyi Peng +3

Notableresearch

Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs

May 12, 2026arXiv codeMadhulatha Mandarapu +1

Notableresearch

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons

May 12, 2026arXiv codeAaron Spieler +2

Notableresearch

Multi-Timescale Conductance Spiking Networks: A Sparse, Gradient-Trainable Framework with Rich Firing Dynamics for Enhanced Temporal Processing

May 12, 2026arXiv codeAlex Fulleda-Garcia +2

NotableresearchARM

Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization

May 12, 2026arXiv codeZhaotian Gu +5

Notableresearch

Most dementia patients have multiple brain diseases. How should they be treated?

May 12, 2026

NotableresearchARM

Peripheral control enabled by distributed sensing in an octopus-inspired soft robotic arm for autonomous underwater grasping

May 12, 2026

Notableresearch

ELF: Embedded Language Flows

May 11, 2026arXiv codeKeya Hu +5

Notableresearch

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

May 11, 2026arXiv codeHaoyuan Sun +5

Notableresearch

Personal Visual Context Learning in Large Multimodal Models

May 11, 2026arXiv codeZihui Xue +4

Notableresearch

Variational Inference for Lévy Process-Driven SDEs via Neural Tilting

May 11, 2026arXiv codeYaman Kindap +4

NotableresearchHugging Face

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

May 11, 2026arXiv codeChenyang Song +5

NotableresearchHugging Face

Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime

May 11, 2026arXiv codeAlbert Alcalde +3

Notableresearch

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

May 11, 2026arXiv codeJunhao Shen +3

Notableresearch

Pixal3D: Pixel-Aligned 3D Generation from Images

May 11, 2026arXiv codeDong-Yang Li +5

NotableresearchUiPath

Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges

May 11, 2026arXiv codeUsman A. Khan +1

Notableresearch

Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character Recognition

May 11, 2026arXiv codeMd. Sultan Al Rayhan +1

NotableresearchMeta

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

May 11, 2026arXiv codeSimon Yu +5

Notableresearch

WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

May 11, 2026arXiv codeShuangrui Ding +5

Notableresearch

Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis

May 11, 2026arXiv codeRichie Yeung +2

Notableresearch

Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients

May 11, 2026arXiv codeAlex DeWeese +1

Notableresearch

Engineering Robustness into Personal Agents with the AI Workflow Store

May 11, 2026arXiv codeRoxana Geambasu +5

Notableresearch

DataMaster: Towards Autonomous Data Engineering for Machine Learning

May 11, 2026arXiv codeYaxin Du +5

Notableresearch

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

May 11, 2026arXiv codeWenxuan Song +5

Majorresearch

Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers

May 11, 2026arXiv codeNikita Kezins +3

NotableresearchMeta

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

May 11, 2026arXiv codeGaotang Li +5

Notableresearch

V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction

May 11, 2026arXiv codeMarcin Kostrzewa +5

Notableresearch

Counterfactual Stress Testing for Image Classification Models

May 11, 2026arXiv codeMoritz Stammel +4

Notableresearch

Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking

May 11, 2026arXiv codeReza Khanmohammadi +5

Notableresearch

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why

May 11, 2026arXiv codeMohammadreza Armandpour +5