Distill Whisper Explained - Robust Knowledge Distillation for Speech Recognition
Explore Distill-Whisper: a compact, efficient speech recognition model. Learn about its robust knowledge distillation, large-scale pseudo labelling, and performance compared to the larger Whisper model.
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Explore OpenMoE, an open-source Mixture-of-Experts language model series. Discover its cost-effectiveness, routing mechanisms, and key insights in comparison to dense LLMs.
SparQ Attention: Bandwidth-Efficient LLM Inference
Explore SparQ Attention, a technique for increasing LLM inference throughput by reducing memory bandwidth in attention blocks through selective history fetching, applicable to off-the-shelf models without retraining.
DSPy Explained - Compiling Declarative Language Model Calls into Self-Improving Pipelines
Explore DSPy, a programming model for LM pipelines that enables self-improving AI systems through declarative modules and computational graphs. Learn its potential to enhance AI performance.
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Explore LayerSkip, an LLM acceleration method that speeds up inference by strategically restricting model layers, achieving 2x speed-ups on various tasks through innovative techniques.
ReFT: Representation Finetuning for Language Models Explained
Explore ReFT, a novel approach to fine-tuning language models by modifying internal representations, achieving efficiency with fewer parameters than traditional methods.
Towards Monosemanticity: Decomposing Language Models with Dictionary Learning
Explore monosemanticity in neural networks through sparse autoencoders. Learn how extracting interpretable features enhances understanding of language model behavior and improves reasoning capabilities.
Complex Agentic RAG Systems - Overcoming Limitations of Traditional RAG
Explore advanced agentic RAG systems with expert Atita Arora, overcoming traditional limitations and revolutionizing information retrieval for AI and machine learning applications.
Hierarchical Prompting Taxonomy - A Universal Evaluation Framework for Large Language Models
Explore a universal evaluation framework for large language models using Hierarchical Prompting Taxonomy. Gain insights into assessing dataset complexity and model capabilities.
Knowledge Circuits in Pretrained Transformers Explained
Explore knowledge circuits in pretrained transformers, uncovering computational mechanisms behind language models' articulation of specific knowledge. Gain insights into AI's inner workings.
Supporting Clinical and Translational Researchers with Electronic Patient Data - Grand Rounds 10/11/22
Explore electronic patient data utilization in clinical and translational research with Dr. Thomas Campion's insights on supporting researchers effectively.
The Future of Imaging Informatics - Enabling the Quintuple Aim in Healthcare
Explore imaging informatics with Dr. Tessa Cook, covering its role in healthcare's quintuple aim, hot topics, cutting-edge research, and strategies for improving patient care and physician experience.
Clinical Informatics, AI, and Multi-modal Analyses in Healthcare - Grand Rounds 2/9/23
Explore AI, predictive biomarkers, and data integration in clinical informatics with Dr. Joel Saltz, discussing cutting-edge tools for investigators in biomedical research.
Modelling Human Syntax by Means of Probabilistic Dependency Grammars - 2007
Explore probabilistic dependency grammars for modeling human syntax, addressing linguistic phenomena beyond context-free grammars and discussing generative models and parsing algorithms.
Connecting Vision and Language End-to-End - 2018
Explore neural models for vision-language understanding, focusing on End-to-End Module Networks and dense video captioning. Learn about interpretable, compositional approaches to visual question answering.
Reducing Confusions and Ambiguities in Speech Translation - 2005
Explore techniques to enhance speech translation by addressing accent-related confusions, named entity recognition, and semantics-based disambiguation for improved accuracy and understanding.
Modeling Common Ground for Multimodal Communication - 2018
Explore multimodal communication in human-machine interactions using a 3D simulation platform. Learn about VoxML modeling language for encoding objects and actions in shared task environments.
Adversarial Machine Learning: Beyond Manipulating Pixels and Words
Explore vulnerabilities in sequential machine learning and challenge assumptions about imperceptible attacks on image classification through human behavioral studies.
Syntactic Language Modeling for Machine Translation and Speech-Repair Detection - 2005
Explore syntactic language modeling techniques for improving machine translation and detecting speech repairs in natural language processing.
Tutorial on Hidden Markov Models - Part 2
Explore advanced concepts of Hidden Markov Models, including applications and algorithms, in this in-depth continuation of Jason Eisner's tutorial series.
Norms and Exploitations: Mapping Meaning onto Use
Explore Corpus Pattern Analysis to map word meanings to typical contexts, reducing lexical entropy and linking patterns to applications like synonym sets or translations.