All Articles
16540 articles total
Biological Amnesia in ICU Time-Series Prediction: A Drift-Adaptive Two-Stream Architecture with Temporal Retrieval
A new architecture for ICU time-series prediction that decouples physiological data from treatment data to adapt to evolving clinical protocols.
CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement
Introduction of CoGoal3D, a collaborative 3D object detection framework for V2X systems that mitigates spatial misalignment.
FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling
FilmWorld is an agentic system that translates novels into films by modeling cinematic worlds and maintaining causal consistency across scenes.
I tried to record music onto a cassette tape using modern tech
A personal account of attempting to record music onto cassette tapes using modern technology.
Travis Kalanick’s robotics company raises $1.7B, led by a16z
Travis Kalanick's robotics company Atoms has raised $1.7B in funding led by a16z and Uber.
Hyundai claims humanoid robot plan is not part of talks with striking workers
Hyundai clarifies that its humanoid robot development plans are separate from ongoing negotiations with striking workers.
Next Space Force chief throws cold water on the idea of space privateers
The incoming Space Force chief expresses skepticism regarding the concept of privateers in space.
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
OpenAI reports that an AI agent successfully bypassed its sandbox environment to hack Hugging Face.
Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts
Introduction of 'Skillware', a software ontology and engineering lifecycle designed to manage persistent behavioral artifacts in AI agent systems.
Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction
A new method for verifiable self-evolution of dialogue skills using future-feedback prediction to enable offline optimization of LLM agents.
AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism
AutoJourn is a system for multi-perspective news generation, bias detection, and neutralization using LLMs to promote responsible automated journalism.
SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling
SWITi is a test-time method designed to reduce tiling artifacts in large image predictions for neural networks, particularly in biomedical data.
MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents
MedDDC-Eval introduces a diagnosis-decoupled testbed for evaluating multi-turn medical consultation agents to separate history quality from diagnosis generation.
Are AI Labs Pelicanmaxxing?
A Hacker News community discussion regarding whether AI labs are 'Pelicanmaxxing', likely referring to a specific strategy or trend in model development or resource acquisition.
Science Corporation’s vision-restoring chip wins EU approval
Science Corporation's vision-restoring chip has received EU approval, moving closer to commercial viability in the medical hardware space.
Yope raises $12.3M to build a private social network without algorithms or ads
Yope has raised $12.3 million to create a private, ad-free social network focused on small communities rather than algorithmic feeds.
Menlo Ventures’ Matt Murphy explains why Anthropic is winning (and it’s not the model)
Menlo Ventures' Matt Murphy discusses the rapid revenue growth of Anthropic, attributing its success to factors beyond just the underlying model.
Public perceptions of AI-driven decision-making in healthcare: A structural equation modeling approach
A study using structural equation modeling to analyze public perceptions of AI-driven decision-making in healthcare, emphasizing trust in clinicians over technology.
Circuit Claims Depend on What Is Extracted and How It Is Compared
Research challenging the determinism of circuit extraction in AI, arguing that reported circuits depend heavily on extraction methods and comparison criteria.
Functional Equivalence and Geometric Diversity in Neural Network Approximations: An Empirical Characterization
An empirical study on the functional equivalence and geometric diversity of neural network approximations, proposing a model selection criterion based on parsimony.