All Articles
18617 articles total
Seven Perfect Shuffles Randomize a Deck of Cards. But How Many Sloppy Ones?
A mathematical exploration of card shuffling and the difference between perfect and sloppy shuffles.
Pixi’s new iOS app turns text messages into interactive AR experiences
Pixi has launched a new iOS app that transforms text messages into interactive augmented reality experiences.
Waymo recalls nearly 4,000 robotaxis to stop them driving into highway construction zones
Waymo recalls nearly 4,000 robotaxis to prevent them from driving into highway construction zones.
This Ghost in the Shell keyboard makes me want to activate the hundred spidery robot fingers inside my regular fingers
Review of the Iqunix Ghost in the Shell edition Hall effect keyboard, highlighting its anime design and build quality.
LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis
Introduction of LandslideAgent and LandslideBench, a multimodal framework and dataset for autonomous landslide identification and analysis.
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
NeuralMUSIC introduces a hybrid neural-subspace framework for improving robot sound source localization in dynamic environments.
scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering
The scGTN framework uses a deep Siamese Graph Transformer Network for more accurate single-cell RNA sequencing clustering.
Bounded Context Management for Tabular Foundation Models on Stream Learning
The CURE policy improves context management for tabular foundation models in stream learning scenarios.
Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow
DCGWM proposes a partitioned latent space and inward-only gradient flow to prevent Objective Interference Collapse in JEPA-based world models.
MIDS: Detecting Stealthy Masquerade and Tampering Attacks on CAN Bus via Bidirectional Mamba
Researchers propose MIDS, a dual-stream framework using bidirectional Mamba state-space models to detect stealthy masquerade attacks on automotive CAN buses.
Steerable Cultural Preference Optimization of Reward Models
The SCPO algorithm is introduced to train reward models that incorporate diverse cultural preferences in LLMs, reducing bias and increasing data efficiency.
QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
QC-GAN is a parameter-efficient speech enhancement framework using Quaternion Conformers and MetricGAN to achieve high fidelity with significantly fewer parameters.
Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance
PhysAssistBench is a new benchmark for evaluating how LLMs assist physicians by coordinating clinical knowledge, EHR interaction, and patient communication.
AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice
A study demonstrates an AI-driven system using Gemini-2.5-pro to link human tutor training performance with real-life tutoring practice through transcription analysis.
Code-Augur: Agentic Vulnerability Detection via Specification Inference
Code-Augur introduces a security-specification-first paradigm for agentic vulnerability detection, using runtime falsification to ground LLM reasoning.
BCL: Bayesian In-Context Learning Framework for Information Extraction
BCL is a Bayesian In-Context Learning framework for information extraction that uses particle filtering to refine label representations.
EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation
EffiNav fuses depth and vision-language models to improve the efficiency and robustness of object goal navigation for autonomous agents.
PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
PEC-Home introduces a simulated dataset to help LLM-based home assistants better interpret progressively elliptical commands in smart home dialogues.
Augmenting Dysarthric Speech Severity Assessment with MOS Supervision
This research proposes augmenting dysarthric speech assessment models using MOS supervision from speech synthesis evaluation data to overcome clinical data scarcity.
Vinyl Cache and Varnish Cache
A Hacker News discussion regarding the differences and use cases for Vinyl Cache and Varnish Cache.