Hovhannes Tamoyan / tamohannes

Hovhannes Tamoyan, Hendrik Schuff, Iryna Gurevych

Lili Yu, Bowen Shi, Ramakanth Pasunuru, Benjamin Muller, Olga Golovneva, Tianlu Wang, Arun Babu, Binh Tang, Brian Karrer, Shelly Sheynin, Candace Ross, Adam Polyak, Russell Howes, Vasu Sharma, Puxin Xu, Hovhannes Tamoyan, Oron Ashual, Uriel Singer, Shang-Wen Li, Susan Zhang, Richard James, Gargi Ghosh, Yaniv Taigman, Maryam Fazel-Zarandi, Asli Celikyilmaz, Luke Zettlemoyer, Armen Aghajanyan

Gayane Chilingaryan*, Hovhannes Tamoyan*, Ani Tevosyan*, Nelly Babayan, Lusine Khondkaryan, Karen Hambardzumyan, Zaven Navoyan, Hrant Khachatrian, Armen Aghajanyan

Karen Hambardzumyan, Hovhannes Tamoyan, Hrant Khachatrian

Machine learning framework designed with YAML-based configurations, featuring effortless Slurm job submission, experiment tracking, and built-in mainstream functionalities.

Browser extension suite for researchers, designed to manage academic papers library. Key features include metadata extraction, highlight processing, citation BibTeX export, and AI-powered querying.

Open-source experiment tracking tool, designed with flexibility for machine learning workflows. Facilitates detailed monitoring and comparison of experiments.

Natural language processing pipeline, equipped with mainstream abstractions. Supports a diverse array of NLP tasks.

• 07. Tokenizers
• 08. Neural Language Models: RNN to LSTM
• 09. Transformers Decoder-only (GPT)
• 10. Encoder-only (BERT) and Seq2seq (T5) Modeling Decoding Strategies
• 11. Pre-Training and Fine-Tuning
• 12. Experiment Reproducibility and NLP Pipeline Debugging

Explore the essentials of experiment tracking in ML research. This presentation covers the key requirements for effective tools and offers an in-depth exploration of Aim. It includes a practical demonstration where Aim is integrated into an NMT system's fine-tuning pipeline.

This session introduces various strategies, including efficient dataloader usage, parallel computation, operator fusing, and many more to enhance the speed and efficiency of your PyTorch code.

• 01. Building Blocks of CNNs: Convolution and Pooling Deep Dive
• 02. Mastering Convolutional Neural Networks: Architecture & Applications
• 03. Modern Computer Vision: From Pixels to Understanding
• 04. Sequential Learning: RNNs, LSTM, and GRU Architectures
• 05. From Words to Vectors: Modern Word Embedding Techniques
• 06. Neural Language Models: Predicting and Understanding Text
• 07. Sequence-to-Sequence Learning: Translation and Beyond
• 08. The Transformer Revolution: Attention-Based Architecture
• 09. Creative AI: Understanding Generative Adversarial Networks
• 10. Dimensionality Reduction and Generation with Autoencoders