All Articles
18326 articles total
A Taxonomy of Mental Health and Technology Needs for Alzheimer's and Dementia Caregivers
A study introducing a taxonomy to link mental health needs of Alzheimer's caregivers with appropriate technology-based interventions.
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
Presents OneCanvas, a method for 3D scene understanding in VLMs that aggregates view features onto a single equirectangular panoramic canvas.
Everything Is BOM: Bill of Materials Encyclopedia
A resource providing a comprehensive encyclopedia of Bills of Materials (BOM), useful for understanding hardware components and supply chains.
Zero-Touch OAuth for MCP
A discussion or implementation of a Zero-Touch OAuth mechanism specifically designed for the Model Context Protocol (MCP).
Zork name origin got an update on Wikipedia
A minor update to the Wikipedia page regarding the origin of the name 'Zork'.
Pareto Q-Learning with Reward Machines
Introduces Pareto Q-Learning with Reward Machines (PQLRM), a sample-efficient reinforcement learning algorithm for multi-objective tasks with non-Markovian rewards.
A Technical Taxonomy of LLM Agent Communication Protocols
Presents a technical taxonomy for LLM agent communication protocols to address interoperability challenges in distributed agent networks.
OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
Introduces OrthoReg, an orthogonal regularization method that prevents neural networks from absorbing the symbolic structure in hybrid symbolic-neural dynamical systems.
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
Proposes AdsMind, a closed-loop multi-agent framework for the autonomous discovery of adsorption configurations on catalyst surfaces using MLFF relaxation feedback.
Essential Subspace Merging for Multi-Task Learning
Presents Essential Subspace Merging (ESM), a training-free method for integrating multiple fine-tuned models into a single multi-task model while reducing interference.
A Clinician-Centered Pipeline for Annotation and Evaluation in Ultrasound AI Studies
Describes a clinician-centered pipeline for remote annotation and evaluation of ultrasound AI studies to ensure clinical usability.
Hardware- and Vision-in-the-Loop Validation of Deep Monocular Pose Estimation for Autonomous Maritime UAV Flight
A hardware-validated vision-in-the-loop framework for deep monocular pose estimation used in autonomous maritime UAV flight.
Show HN: Are You in the Weights?
A Show HN project exploring whether a user's identity or data is present within the weights of large language models.
American Express: Cell-Based Architecture for Resilient Payment Systems
American Express shares its implementation of a cell-based architecture to enhance the resilience and scalability of its payment processing systems.
AI inference startup Baseten reportedly raising $1.5B months after its last mega round
AI inference startup Baseten is reportedly raising $1.5 billion in funding to scale its inference capabilities.
Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training
Introduction of Spotlight, a system that utilizes spot GPUs to significantly reduce the cost and time of Reinforcement Learning post-training for Diffusion Transformers.
FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs
FoMoE introduces a system for partitioning expert layers across workers in Mixture-of-Experts architectures to reduce communication costs and memory constraints in distributed training.
A Hybrid LSTM--Vision Transformer Architecture for Predicting HRRR Forecast Errors
A research paper proposing a hybrid LSTM-Vision Transformer architecture to improve the prediction of forecast errors in high-resolution numerical weather prediction systems.
Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
Discusses 'vibe coding' and proposes 'Variability by Regeneration' (VbR), treating LLMs as derivation engines for software product lines to eliminate dead code.
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
ProductConsistency introduces a dataset and reward mechanism to improve product identity preservation and text fidelity in instruction-based image editing.