Hao Liu

ringattention. Large Context Attention

chain-of-hindsight. Simple next-token-prediction for RLHF

language-quantized-autoencoders. Language Quantized AutoEncoders

hybrid-discriminative-generative. Hybrid Discriminative-Generative Training via Contrastive Learning

instructrl. Instruction Following Agents with Multimodal Transforemrs

taming-maml. Taming MAML: efficient unbiased meta-reinforcement learning

tux. Tools and Utils for Experiments (TUX)

mini_apt. Python

jax_sac. Python