-
KAIST
- South Korea
-
13:16
(UTC +09:00) - https://jw9730.github.io
- @jw9730
Highlights
- Pro
Stars
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…
Official code for LLaGA: Large Language and Graph Assistant
Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
A high-throughput and memory-efficient inference and serving engine for LLMs
The repository implements the Transformer over Directed Acyclic Graph (DAG transformer) in Pytorch Geometric.
A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?
Neural Networks and the Chomsky Hierarchy
a structural diff that understands syntax 🟥🟩
Implementation of the "Online learning of long-range dependencies" paper, NeurIPS 2023
NicolasZucchet / minimal-LRU
Forked from lindermanlab/S5Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)
Code for the paper Sheaf Diffusion Goes Nonlinear: Enhancing GNNs with Adaptive Sheaf Laplacians, implementing and testing NLSD model.
Offcial Repo of Paper "Eliminating Position Bias of Language Models: A Mechanistic Approach""
Official code repository of paper Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency.
Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network
Linear and non-linear spectral forecasting algorithms
Official Implementation of ICLR 2024 paper "Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning"
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
Scalable and user friendly neural 🧠 forecasting algorithms.