Welcome to HKU NLP group! We are a group of researchers working on natural language processing in the Department of Computer Science at the University of Hong Kong. Check out our website.
Pinned Loading
-
efficient-attention Public
[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling
-
RSA Public
Forked from chang-github-00/RSA
Retrieved Sequence Augmentation for Protein Representation Learning
-
reparam-discrete-diffusion Public
Reparameterized Discrete Diffusion Models for Text Generation
-
ChunkLlama Public
[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
-
diffusion-of-thoughts Public
[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"
-
DiffuLLaMA Public
[ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Repositories
Showing 10 of 24 repositories
-
- LLM-Predictive-Decoding Public Forked from chang-github-00/LLM-Predictive-Decoding
[ICLR2025] Non-myopic Generation of Language Models for Reasoning and Planning
- DiffuLLaMA Public
[ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models
- diffusion-of-thoughts Public
[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"
- DiffuSearch Public
[ICLR 2025] Code for the paper "Implicit Search via Discrete Diffusion: A Study on Chess"
- diffusion-vs-ar Public
[ICLR 2025] Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"
- ChunkLlama Public
[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
- GSM-Plus Public Forked from qtli/GSM-Plus
GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.