Supervised fine-tuning as a method for training-based AI control
lesswrong.com·1d
🛡️AI Security
Flag this post
An interview with William Kahan, the old man of floating-point. (1998)
💾Retro Computing
Flag this post
🍸 Build Accurate Alcohol Dilution Calculations with This Free Online Tool
💎Refinement Types
Flag this post
Omnidirectional type inference for ML: principality any way
arxiv.org·18h
🎯Hindley-Milner
Flag this post
LODESTAR: Degeneracy-Aware LiDAR-Inertial Odometry with Adaptive Schmidt-Kalman Filter and Data Exploitation
arxiv.org·1d
🧭Inertial Navigation
Flag this post
FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning
arxiv.org·18h
📱Edge AI
Flag this post
A surrogate-based approach to accelerate the design and build phases of reinforced concrete bridges
arxiv.org·1d
🌀Naiad
Flag this post
Automated Ground Settlement Prediction via Deep Learning and Bayesian Calibration in Deep Excavation
🔬Deep Learning
Flag this post
PANDA - Patch And Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning
arxiv.org·18h
📱Edge AI
Flag this post
Tree-Based Stochastic Optimization for Solving Large-Scale Urban Network Security Games
arxiv.org·18h
⚡Incremental Computation
Flag this post
Enhanced Cryogenic Storage Tank Integrity via Adaptive Deep Learning Nondestructive Evaluation
🎯Reinforcement Learning
Flag this post
Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
arxiv.org·18h
🛡️AI Security
Flag this post
Provably Safe Stein Variational Clarity-Aware Informative Planning
arxiv.org·18h
🎯Reinforcement Learning
Flag this post
Loading...Loading more...