Dillon Pulliam

Deep Learning Researcher at AssemblyAI

Deep Learning Paper Recap - Diffusion and Transformer Models
Deep Learning Paper Recap - Diffusion and Transformer Models

This week’s Deep Learning Paper Reviews is Diffusion-LM Improves Controllable Text Generation and Sparsifying Transformer Models with Trainable Representation Pooling.

Review – TOXIGEN & Knowledge Distillation Meets Open-Set Semi-Supervised Learning
Review – TOXIGEN & Knowledge Distillation Meets Open-Set Semi-Supervised Learning

This week’s Deep Learning Paper Reviews are TOXIGEN: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection and Knowledge Distillation Meets Open-Set Semi-Supervised Learning.

Review - Perceiver: General Perception with Iterative Attention
Review - Perceiver: General Perception with Iterative Attention

This week’s Deep Learning Paper Review is Perceiver: General Perception with Iterative Attention.

Review - SimCLS and RefSum - Summarization Techniques
Review - SimCLS and RefSum - Summarization Techniques

This week’s Deep Learning research papers are SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization and RefSum: Refactoring Neural Summarization.

New: Improved Topic Detection and IAB Classification
New: Improved Topic Detection and IAB Classification

We’re excited to release a major accuracy improvement to our Topic Detection feature, which can accurately predict the topics spoken in audio/video files.