Hub / Ai Research
ai-research · WeSearch
Ai Research news.
Page 8 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.
ARXIV CS.AI
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
ARXIV CS.AI
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
ARXIV CS.AI
Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?
ARXIV CS.AI
Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations
ARXIV CS.AI
Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning
ARXIV CS.AI
Graph Alignment Topology as an Inductive Bias for Grounding Detection
ARXIV CS.AI
A mathematical theory of balancing relational generalization and memorization
ARXIV CS.AI
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
ARXIV CS.AI
LLM Code Smells: A Taxonomy and Detection Approach
ARXIV CS.AI
Memorization Dynamics of Fill-in-the-Middle Pretraining
ARXIV CS.AI
Test-Time Training Undermines Safety Guardrails
ARXIV CS.AI
Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
ARXIV CS.AI
A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism
ARXIV CS.AI
Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
ARXIV CS.AI
MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
ARXIV CS.AI
Brain-LLM Alignment Tracks Training Data, Not Typology
ARXIV CS.AI
Uncovering the Latent Potential of Deep Intermediate Representations
ARXIV CS.AI
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
ARXIV CS.AI
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs
ARXIV CS.AI
The TIME Machine: On The Power of Motion for Efficient Perception
ARXIV CS.AI
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
ARXIV CS.AI
Model Collapse as Cultural Evolution
ARXIV CS.AI
Decomposing and Measuring Evaluation Awareness
ARXIV CS.AI
DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks
ARXIV CS.AI
A measurement substrate for agentic Kubernetes operations: Methodology and a case study in retrieval-compounding falsification
ARXIV CS.AI
Anytime Training with Schedule-Free Spectral Optimization
ARXIV CS.AI
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
ARXIV CS.AI
KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
ARXIV CS.AI
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
ARXIV CS.AI
Security of LLM-generated Code: A Comparative Analysis
ARXIV CS.AI
Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Plane Augmentation Study on BRISC 2025
ARXIV CS.AI
A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Collected Works
ARXIV CS.AI
Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study
ARXIV CS.AI
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
ARXIV CS.AI
Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking
ARXIV CS.AI
Defining AI Fatigue in Academic Contexts: Dimensions, Indicators, and a Stage-Based Model Using Grounded Theory
ARXIV CS.AI
Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning
ARXIV CS.AI
CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection
ARXIV CS.AI
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
ARXIV CS.AI
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
ARXIV CS.AI
Generative AI and the Reorganization of Labor Demand
ARXIV CS.AI
Autonomous Frontier-Based Exploration with VLM Guidance
ARXIV CS.AI
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
ARXIV CS.AI
Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
ARXIV CS.AI
Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
ARXIV CS.AI
Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
ARXIV CS.AI
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
ARXIV CS.AI
Lipschitz Optimization for Formal Verification of Homographies
ARXIV CS.AI
FastKernels: Benchmarking GPU Kernel Generation in Production
ARXIV CS.AI