All Articles
17680 articles total
Americans see their country's past, present and future
An article reflecting on the past, present, and future of the United States.
Manufactured Confidence: How Memory Consolidation Turns Hearsay into Confident Facts
Research demonstrates that LLM memory consolidation often converts tentative remarks into confident facts, creating a security vulnerability.
Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning
A study reveals 'intervention bias' in zero-shot LLMs for educational advisory, proposing a supervised policy learning approach using Decision Transformers and XGBoost for better calibration.
Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation
GeoRAG is introduced to optimize information demand coverage in RAG by treating context selection as a distribution optimization problem rather than simple ranking.
From Julia to Rust: a differentiable tensor stack for scientific computing
A discussion on transitioning a differentiable tensor stack for scientific computing from Julia to Rust for improved performance and safety.
Forestiere Underground Gardens
An article about the Forestiere Underground Gardens, which is not technical in nature.
Deriving the SVD (Single Value Decomposition) from scratch
A technical derivation of Single Value Decomposition (SVD) from scratch, providing a deep dive into the linear algebra behind it.
Scaling Laws, Carefully
A critical examination of scaling laws in AI, focusing on a more careful and nuanced approach to their application.
Structural Correctness
A discussion on the concept of structural correctness in software systems, emphasizing formal methods and reliability.
The “Father of the Internet” is finally retiring
Vinton Cerf, a co-creator of the internet's foundational protocols, is retiring from his role at Google.
AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance
Introduction of AnyBody, a humanoid controller that uses arbitrary keypoint guidance for free-form whole-body control.
MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments
MoPe introduces a memory-aware uncertainty filter for monocular Gaussian mapping to improve robot autonomy in dynamic environments.
Confidence-feedback-weighted graph matching network: online-offline laser-induced damage site matching under complex interference
A new graph matching network using confidence-feedback weights to accurately match laser-induced damage sites under interference.
A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment
A hybrid framework for song lyric annotation utilizing human-LLM alignment to handle the subjectivity of emotion recognition.
How Anthropomorphic Language Impacts Public Perceptions of AI
A study investigating whether anthropomorphic language in AI descriptions significantly alters public perception, finding that its immediate effects are modest.
CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection
Introduces CMTFormer, a transformer-based model that hierarchically integrates RGB and event camera data for improved object detection.
GPC: Large-Scale Generative Pretraining for Transferable Motor Control
Presents Generative Pretrained Controllers (GPC), which use tokenization and next-token prediction to create general-purpose controllers for physics-based character animation.
On the Nonlinearity of Learning Rate Scaling for LLM Training
Analyzes learning rate scaling for LLM training, discovering that optimal learning rates exhibit nonlinear curvature at larger scales.
Invariant Reasoning Directions in Latent Trajectories of Language Models
Introduces Trajectory-Invariant Latent Refinement (TILR), a framework to identify and manipulate stable reasoning directions in the latent space of language models.
Projected Exploitability Descent for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games
Proposes Projected Exploitability Descent (PED), a new algorithm for approximating Nash equilibria in multiplayer imperfect-information games.