WeSearch
Hub / Ai Research
ai-research · WeSearch

Ai Research news.

Page 15 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.

ARXIV CS.AI

VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals

5/20/2026 · 12 views
ARXIV CS.AI

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling

5/20/2026 · 10 views
ARXIV CS.AI

An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making

5/20/2026 · 17 views
ARXIV CS.AI

The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next

5/20/2026 · 13 views
ARXIV CS.AI

Graph-Driven Cross-Industry Real-Time Monitoring Framework for Anti-Money Laundering Detection in Converged Mobility-Energy Supply Chain Networks

5/20/2026 · 14 views
ARXIV CS.AI

First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation

5/20/2026 · 13 views
ARXIV CS.AI

Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels

5/20/2026 · 17 views
ARXIV CS.AI

Transformers Linearly Represent Highly Structured World Models

5/20/2026 · 14 views
ARXIV CS.AI

Exact Linear Attention

5/20/2026 · 15 views
ARXIV CS.AI

INSIGHTS: Demonstration-Based Summaries of Time Series Predictors

5/20/2026 · 13 views
ARXIV CS.AI

KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat

5/20/2026 · 16 views
ARXIV CS.AI

Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

5/20/2026 · 15 views
ARXIV CS.AI

The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection

5/20/2026 · 11 views
ARXIV CS.AI

When Individually Calibrated Models Become Collectively Miscalibrated

5/20/2026 · 11 views
ARXIV CS.AI

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

5/20/2026 · 13 views
ARXIV CS.AI

Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables

5/20/2026 · 14 views
ARXIV CS.AI

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

5/20/2026 · 14 views
ARXIV CS.AI

From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation

5/20/2026 · 12 views
ARXIV CS.AI

FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives

5/20/2026 · 13 views
ARXIV CS.AI

EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample

5/20/2026 · 7 views
ARXIV CS.AI

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

5/20/2026 · 12 views
ARXIV CS.AI

MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization

5/20/2026 · 10 views
ARXIV CS.AI

Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning

5/20/2026 · 9 views
ARXIV CS.AI

EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly

5/20/2026 · 12 views
ARXIV CS.AI

AgentWall: A Runtime Safety Layer for Local AI Agents

5/19/2026 · 12 views
ARXIV CS.AI

ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

5/19/2026 · 13 views
ARXIV CS.AI

From Prompts to Protocols: An AI Agent for Laboratory Automation

5/19/2026 · 13 views
ARXIV CS.AI

Skim: Speculative Execution for Fast and Efficient Web Agents

5/19/2026 · 11 views
ARXIV CS.AI

Scalable Uncertainty Reasoning in Knowledge Graphs

5/19/2026 · 18 views
ARXIV CS.AI

Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators

5/19/2026 · 13 views
ARXIV CS.AI

PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation

5/19/2026 · 14 views
ARXIV CS.AI

TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens

5/19/2026 · 16 views
ARXIV CS.AI

Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents

5/19/2026 · 13 views
ARXIV CS.AI

LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning

5/19/2026 · 18 views
ARXIV CS.AI

Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment

5/19/2026 · 18 views
ARXIV CS.AI

Recall Isn't Enough: Bounding Commitments in Personalized Language Systems

5/19/2026 · 8 views
ARXIV CS.AI

GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction

5/19/2026 · 14 views
ARXIV CS.AI

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

5/19/2026 · 14 views
ARXIV CS.AI

A Global-Local Graph Attention Network for Traffic Forecasting

5/19/2026 · 11 views
ARXIV CS.AI

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

5/19/2026 · 14 views
ARXIV CS.AI

Body-Grounded Perspective Formation and Conative Attunement in Artificial Agents

5/19/2026 · 8 views
ARXIV CS.AI

State Contamination in Memory-Augmented LLM Agents

5/19/2026 · 14 views
ARXIV CS.AI

NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

5/19/2026 · 15 views
ARXIV CS.AI

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework

5/19/2026 · 19 views
ARXIV CS.AI

Voices in the Loop: Mapping Participatory AI

5/19/2026 · 13 views
ARXIV CS.AI

Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models

5/19/2026 · 15 views
ARXIV CS.AI

Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence

5/19/2026 · 7 views
ARXIV CS.AI

Learning to Learn from Multimodal Experience

5/19/2026 · 13 views
ARXIV CS.AI

Reasoning Can Be Restored by Correcting a Few Decision Tokens

5/19/2026 · 9 views
ARXIV CS.AI

Virtual Nodes Guided Dynamic Graph Neural Network for Brain Tumor Segmentation with Missing Modalities

5/19/2026 · 17 views

Sources in Ai Research

Other categories