Hanlin Wang

SPA-RL-Agent. Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"

STeCa. (ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"

EVU. (ACL2026 Findings) Official code for the paper "Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents"

COMP6704-Individual-Project. Individual Project for COMP6704: Optimization

E2CL. (EMNLP24 Findings) Official code for the paper "E2CL: Exploration-based Error Correction Learning for Embodied Agents"

moco. PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

perfect. PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.

tuning_playbook_zh_cn. 一本系统地教你将深度学习模型的性能最大化的战术手册。

event_detection_without_triggers. Python

huggingface_hub. All the open source things related to the Hugging Face Hub.

adapter-transformers. Huggingface Transformers + Adapters = ❤️

eeqa. Event Extraction by Answering (Almost) Natural Questions