🦜🔗 Build context-aware reasoning applications

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Instruct-tune LLaMA on consumer hardware

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

links to conference publications in graph-based deep learning

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Diffusion attentive attribution maps for interpreting Stable Diffusion.

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

code to analyze the legal citation network

Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks (KDD 2023)

Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy (WWW'24)