Zhaorun Chen's Projects
Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
Config files for my GitHub profile.
This repository contains the algorithms implementation for vehicles scheduling, dispatching and planning in complicated scenarios such as intersection, junction etc. Currently we are developing learnable driving policies module via inverse reinforcement learning algorithms.
This repository is for backups for Professor David Gleich's course CS520 in Fall 2023 at Purdue.
Purdue Spring23 CS593 Project
[ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"
a learn-from-demonstration framework for on-policy actor-critic reinforcement learning algorithms
Official implementation for "MJ-BENCH: Is Your Multimodal Reward Model Really a Good Judge?"
The implementation for the integrated SRL-RL algorithm POAR as well as the simulator for environments
applying both traditional and heuristics methods to pottery relics restoration (fragments matching, 3D model alignment)
established for the data normalization and reinforcement learning training scheme to train an agent in DCS world
Applying IRL algorithms to learn robot arm motion planning from human demonstration
SafeRLZoo, a standardized toolkit with over 12 SOTA model-free safe RL algorithms based on Spinningup and benchmark safety-critical tasks
Train transformer language models with reinforcement learning.
This project mainly develops a visualization platform aiming to process and present the medical data of Greyout/Redout to analyze this symptom and its causes both qualitatively and quantitatively.