All Articles
18326 articles total
Advanced Compilers: The Self-Guided Online Course
A self-guided online course focused on advanced compiler design and implementation.
Leveraging Energy Features for Surface Classification with Deep Learning: A Comparative Analysis Across Three Independent Datasets
Research comparing deep learning architectures for surface classification in mobile robotics using energy-derived features.
TW-LegalBench: Measuring Taiwanese Legal Understanding
Introduction of TW-LegalBench, a benchmark for evaluating the legal reasoning capabilities of LLMs within the Taiwanese legal system.
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish
Morpheus is a neural morpheme-boundary model for Turkish that provides lossless tokenization and efficient word embeddings.
Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring
The GGATN architecture is proposed for predictive process monitoring, using graph-grounded cross attention for event sequence generation.
Two-Phase Bilevel Search for the Moving-Target Traveling Salesman Problem with Moving Obstacles
A Two-Phase Bilevel Search (TPBS) algorithm is presented to solve the Moving-Target Traveling Salesman Problem with Moving Obstacles.
SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents
SWE-Future proposes a data synthesis method for coding agents that forecasts future repository needs to create realistic benchmarks.
Generating Natural and Expressive Robot Gestures through Iterative Reinforcement Learning with Human Feedback using LLMs
Using RLHF and LLMs to generate more natural and expressive co-speech gestures for the Pepper humanoid robot.
Challenging the Narrative of European Decline
A discussion on Hacker News regarding the narrative of European decline.
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.