Zhiyuan Hu

UoT. [NeurIPS 2024] Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

Meta-Ability-Alignment. Official code of paper "Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models"

LongRecipe. LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

AAAI-19_slide_poster.

Long_form_VideoQA. [EMNLP’24 Main] Encoding and Controlling Global Semantics for Long-form Video Question Answering

MATTRL.

ProToD.

Uniqueness-Aware-RL.

longLLM-Extrapolation-Papers.

Generating-Chinese-Ci. This repository is about Chinese Ci(宋词) generation, and the paper has been accepted by AAAI-19

LLM-Agent-Paper-List. The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

social-reasonser.

PPO-PyTorch. Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Visualizing-and-Understanding-Neural-Models-in-NLP. Lua