Blog Posts
RSS- Jun 2, 2026, 09:45: Frequency-Weighted Neural Kalman Filters #inertial-motion-capture #papers
- May 19, 2026, 13:58: paper-reproductions #training-infrastructure
- Apr 20, 2026, 10:38: Offline and Model-Based RL: CQL, Decision Transformer, DPO, and World Models #model-based-rl #offline-rl
- Mar 21, 2026, 16:40: Actor-Critic and Distributed RL: DDPG, TD3, SAC, and Beyond #actor-critic
- Feb 19, 2026, 18:26: Sparse Inertial Motion Capture: IMU Models, Orientation, and Sensor Fusion #inertial-motion-capture
- Feb 6, 2026, 14:58: Trust-Region Policy Methods: TRPO, PPO, and GRPO #policy-gradient
- Feb 5, 2026, 21:10: torchestrator #design-patterns #training-infrastructure
- Jan 9, 2026, 18:34: Policy Gradients: REINFORCE, Baselines, and Generalized Advantage Estimation #policy-gradient
- Nov 14, 2025, 18:22: Quantization-Aware Training: Scales, Granularity, and Calibration #quantization
- Jun 20, 2025, 09:19: Bayesian Optimization with Gaussian Process Surrogates #bayesian-optimization #gaussian-processes
- May 8, 2025, 10:12: Beyond Subjectivity: Continuous Cybersickness Detection Using EEG #papers
- Apr 25, 2025, 21:36: Gaussian Processes and Deep Kernel Learning #gaussian-processes
- Apr 16, 2025, 11:56: Uncertainty Quantification: Predictive Variance, MC Dropout, and Deep Ensembles #uncertainty-quantification
- Mar 27, 2025, 15:25: Posterior Approximation: Variational Inference from Mean-Field to Cold Posteriors #bayesian-neural-networks
- Feb 25, 2025, 15:45: Bayesian Neural Networks: Evidence, HMC, and Function-Space Bayes #bayesian-neural-networks
- Jan 10, 2025, 16:38: Probabilistic Deep Learning Foundations: Tractability versus Generality #probabilistic-ml
- Dec 11, 2024, 15:32: Neural Scaling Laws: Kaplan, Chinchilla, and Compute-Optimal Training #scaling-laws
- Nov 26, 2024, 19:54: Benign Overfitting and Double Descent #double-descent
- Oct 10, 2024, 19:27: The Neural Tangent Kernel and Infinite-Width Networks #neural-tangent-kernel
- Oct 1, 2024, 11:30: Bucketed Ranking-Based Losses for Efficient Training of Object Detectors #object-detection #papers
- Sep 26, 2024, 09:52: Differentiating Through Constrained Optimization: Implicit Layers and Convex Programs #constrained-optimization
- Aug 6, 2024, 16:13: PAC-Bayes Generalization Bounds: From McAllester to Nonvacuous Bounds #pac-bayes
- Jul 1, 2024, 00:02: registry-pattern #design-patterns
- Jun 6, 2024, 22:59: Vision-Language Models: CLIP, ALIGN, and SigLIP #vision-language-models
- May 18, 2024, 15:47: Self-Supervised Representation Learning: Instance Discrimination and InfoNCE #self-supervised-learning
- Apr 2, 2024, 19:49: Knowledge Distillation: Soft Labels, Temperature, and Dark Knowledge #knowledge-distillation
- Feb 4, 2024, 11:48: Optimal Transport: From Exact Linear Programs to Sinkhorn and Neural Potentials #optimal-transport
- Dec 8, 2023, 20:30: Detection and Segmentation Transformers: DETR and Its Descendants #object-detection #segmentation #vision-transformers
- Oct 6, 2023, 12:40: Diffusion Models and DiT: Noise Schedules, DDIM, and Scalable Transformers #diffusion-models
- Sep 10, 2023, 17:14: Vision Transformers: ViT, Self-Attention, and the CNN Comparison #vision-transformers
- Jul 17, 2023, 15:40: Autoregressive Image Generation: PixelRNN, PixelCNN, and VQ-VAE #deep-generative-models
- Jun 2, 2023, 22:30: CNN Object Detection: From LeNet and AlexNet to Modern Detector Backbones #object-detection
- Apr 19, 2023, 22:35: Variational Autoencoders: The ELBO and the Reparameterization Trick #deep-generative-models
- Mar 13, 2023, 10:02: Classical Statistical Learning: ERM, Capacity Control, and Uniform Convergence #statistical-learning
- Jan 24, 2023, 21:33: observer-pattern #design-patterns
- Sep 16, 2019, 02:52: torchdatasets #datasets
