Physics in Video Language Models
In this post, we explore the physics behind text to video language models and how they can be used to generate realistic videos from text prompts. Read more
Blog
2024
Tokenization: The Red Pill to see past The Matrix
Tokenization is a necessary and often overlooked component in large language models. In this post, we explore the importance of tokenization and how it might very well be the key to unlocking the advanced abilities of what we expect AI to be in the future. Read more
Open-ended vs Descriptive Prompting: Finding the right balance in your AI use-cases
When working with language models, the way we phrase our prompts can dramatically affect the quality and usefulness of the responses we receive. In this post we explore the dichotomy in setting up prompts - being open-ended vs descriptive - and understand the implication of each. Read more
Understanding MLPs as Hashing Functions: A Geometric Perspective
When we think about Multi-Layer Perceptrons (MLPs), we often visualize them as interconnected neurons processing information. However, there’s an elegant alternative perspective - viewing MLPs as hashing functions that partition input space and mapping functions on these partitions. Read more
Part 2 - The Hidden Geometry of Large Language Models: A New Perspective on Reasoning
At Tenyx, we’ve delved into the intricate workings of Large Language Models (LLMs) to uncover the geometric structures underlying their reasoning capabilities. Our research provides new insights into how LLMs process information and the implications for improving their reasoning abilities. Read more
Part 1 - The Hidden Geometry of Large Language Models: Implications on Safety & Toxicity
At Tenyx, we’ve spent countless hours peering into the intricate workings of Large Language Models (LLMs). Today, we’re excited to share our research, in collaboration with Brown University, that sheds light on the geometric structures and transformations governing these models. Our work provides new insights into how LLMs process their inputs and the implications for AI safety in applications driven by LLMs. Read more
2023
Forgetting and Toxicity in LLMs: A Deep Dive on Fine-Tuning Methods
Fine-tuning is a common procedure by which a pretrained language model is updated with training on a domain-specific dataset to improve performance in that domain (i.e. a chatbot to answer enterprise-specific Q&A, a hotel booking agent). It has been known for some time (if not widely appreciated) that fine-tuning a model on new data degrades its performance on the initial pretraining dataset (the dreaded “catastrophic forgetting” problem in ML). But by how much? And do all fine-tuning methods degrade performance in the same ways, and to the same extent? Read more
2021
Revisiting k-nearest neighbor benchmarks in self-supervised learning
Standard protocols for benchmarking self-supervised models involve using a linear or k-nearest neighbor classification on frozen features of the learned model. However, both evaluations are sensitive to hyperparameters making the evaluation and comparison complicated. Read more
2020
Efficient graph construction to represent images
Image processing over the years has evolved from simple linear averaging filters to highly adaptive non linear filtering operations such as the bilateral filter (BF), moving least squares, BM3D and LARK to name a few. Read more
Representing data using graphs: A sparse signal approximation view
Graph driven machine learning has seen a surge of interest in the past few years with several applications in social sciences, biology, and network analysis, to name a few. However, in some scenarios, no graph is given a priori and one one has to infer and construct a graph to fit the data given. Read more
2017
Difficulties in training a Generative Adversarial Network
Generative modeling is a branch of machine learning that attempts at modeling the probability distribution of high dimensional data, for example - images Read more
2016
A notion of uncertainty in modern neural networks
In this post, we will look at a particular view of uncertainty in modern deep learning systems using droput Read more
A preliminary on generative modeling using neural networks
Generative modeling is a branch of machine learning that attempts at modeling the probability distribution of high dimensional data, for example - images Read more
Neural network compression using optimal brain damage
Model pruning in neural networks was the answer I ended up with when I got wondering about the workings of dropout, dropconnect and papers like Do Deep Nets Really Need to be Deep? Read more
A brief introduction to activation functions in neural networks
Neural networks can be viewed as layers of building blocks neurons made up of weights, biases and activation function. A fundamental understanding of how these basic units function could help one in achieving one’s objective Read more