Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

This is the repository for paper EscapeBench: Pushing Language Models to Think Outside the Box

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

A generative world for general-purpose robotics & embodied AI learning.

Demo-Driven Mobile Bi-Manual Manipulation Benchmark.

A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

OGBench: Benchmarking Offline Goal-Conditioned RL

Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"

Guide for surviving at UIUC (under development)

Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.

Official implementation of Diffusion Model-Based Predictor (DMBP) presented in ICLR2024.

Course Material for the UG Course COMP4901Y

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Word2World is an LLM-based PCG system that creates playable 2D world from stories

[ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"

Recipes to train reward model for RLHF.

The Paper List on Data Contamination for Large Language Models Evaluation.

Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

Code for ICLR 2024 paper "Towards Robust Offline Reinforcement Learning under Diverse Data Corruption"

Prompt Learning using Metaheuristics

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

Latent-based SR using MoE and frequency augmented VAE decoder

An environment based on JSBSIM aimed at one-to-one close air combat.