optimization

• Implementing DistBelief 08 Aug 2018
• Constraint Satisfaction Solver 27 Aug 2017
• Simulated Annealing 13 Feb 2017
• Genetic Algorithms 15 Jul 2016

machine-learning

• To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training 05 Feb 2026
• When Quantization Isn't Enough: Why 2:4 Sparsity Matters 06 Oct 2025
• TorchAO: PyTorch-Native Training-to-Serving Model Optimization 21 Jul 2025
• Accelerating Transformer Inference and Training with 2:4 Activation Sparsity 20 Mar 2025
• Lightning Talk: Sparsifying Vision Transformers with Minimal Accuracy Loss 01 Sep 2024
• Accelerating Neural Network Training with Semi-Structured (2:4) Sparsity 20 Jun 2024
• Speeding up ViTs using Block Sparsity 14 May 2024
• (beta) Accelerating BERT with semi-structured (2:4) sparsity 22 Apr 2024
• Lecture 11: Sparsity 03 Apr 2024
• Leveraging Neural Embeddings: Part V 01 Nov 2021
• Leveraging Neural Embeddings: Part IV 19 Oct 2021
• Leveraging Neural Embeddings: Part III 12 Oct 2021
• Leveraging Neural Embeddings: Part II 01 Oct 2021
• Leveraging Neural Embeddings: Part I 23 Sep 2021
• Learning Embeddings from Cooccurence Matrices 03 Jan 2020
• BERT fine-tuning and Contrastive Learning 30 Aug 2019
• Learning Better Sentence Representations 19 May 2019
• Implementing DistBelief 08 Aug 2018
• Variational Autoencoders 15 May 2018
• Generative Models 05 May 2018
• Ensemble Methods 12 Jan 2018
• Using RNNs to predict user submission 13 Dec 2017
• Graphical Models 13 Jul 2017
• Machine Learning 13 Jun 2017
• CS188 Project 08 Jun 2017
• Configuring a ML Server 23 May 2017
• CS188 Literature Review 24 Apr 2017
• Twitter Tensorflow Sentiment Analysis 11 Jan 2017
• Deepdive 03 Jan 2017

probabilistic-models

• Variational Autoencoders 15 May 2018
• Reasoning Under Uncertainity 13 Aug 2017
• Graphical Models 13 Jul 2017
• Deepdive 03 Jan 2017

nlp

• Leveraging Neural Embeddings: Part V 01 Nov 2021
• Leveraging Neural Embeddings: Part IV 19 Oct 2021
• Leveraging Neural Embeddings: Part III 12 Oct 2021
• Leveraging Neural Embeddings: Part II 01 Oct 2021
• Leveraging Neural Embeddings: Part I 23 Sep 2021
• Learning Embeddings from Cooccurence Matrices 03 Jan 2020
• BERT fine-tuning and Contrastive Learning 30 Aug 2019
• Learning Better Sentence Representations 19 May 2019
• CS188 Project 08 Jun 2017
• CS188 Literature Review 24 Apr 2017
• Twitter Tensorflow Sentiment Analysis 11 Jan 2017

misc

• Medical Imaging Techniques 21 Sep 2017
• Image Processing 27 May 2017
• Configuring a ML Server 23 May 2017
• Artificial Intelligence 08 May 2017
• Computer Graphics 04 May 2017
• Dockerizing Web Applications 12 Apr 2017
• CICD on AWS 08 Apr 2017
• ACM AI in Review 04 Mar 2017
• Acm Reading List 2017 11 Feb 2017
• Corporate Finance 28 Jan 2017

algorithms

• Logic 13 Nov 2017
• Constraint Satisfaction 12 Oct 2017
• Search 03 Jun 2017
• Reduction And Intractibility 16 Mar 2017
• Randomness 14 Mar 2017
• Divide And Conquer 06 Mar 2017
• Dynamic Programming 25 Feb 2017
• Greedy Algorithms 23 Feb 2017

theory

• Building $\mathbb{Q}$ visually 04 Apr 2019
• Languages and Automata 13 Nov 2018
• Variational Autoencoders 15 May 2018
• Generative Models 05 May 2018
• Caching 03 Apr 2018
• Ensemble Methods 12 Jan 2018
• Reduction And Intractibility 16 Mar 2017
• Randomness 14 Mar 2017

systems

• Implementing DistBelief 08 Aug 2018
• Caching 03 Apr 2018
• Computer Systems Architecture 30 Jul 2017

startups

• Startup Equity Primer 20 Mar 2020
• Blend 20 Sep 2018

mathematics

• Building $\mathbb{Q}$ visually 04 Apr 2019

research

• Learning Embeddings from Cooccurence Matrices 03 Jan 2020
• BERT fine-tuning and Contrastive Learning 30 Aug 2019

talks

• Lightning Talk: Sparsifying Vision Transformers with Minimal Accuracy Loss 01 Sep 2024
• Lecture 11: Sparsity 03 Apr 2024

pytorch

• To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training 05 Feb 2026
• When Quantization Isn't Enough: Why 2:4 Sparsity Matters 06 Oct 2025
• TorchAO: PyTorch-Native Training-to-Serving Model Optimization 21 Jul 2025
• Accelerating Transformer Inference and Training with 2:4 Activation Sparsity 20 Mar 2025
• Accelerating Neural Network Training with Semi-Structured (2:4) Sparsity 20 Jun 2024
• Speeding up ViTs using Block Sparsity 14 May 2024
• (beta) Accelerating BERT with semi-structured (2:4) sparsity 22 Apr 2024

papers

• To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training 05 Feb 2026
• TorchAO: PyTorch-Native Training-to-Serving Model Optimization 21 Jul 2025
• Accelerating Transformer Inference and Training with 2:4 Activation Sparsity 20 Mar 2025