CostNav: A Navigation Benchmark for Cost-Aware Evaluation of Embodied Agents

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

A feature-rich command-line audio/video downloader

Efficiently apply modification functions to RLDS/TFDS datasets.

LLM/VLM gaming agents and model evaluation through games.

A Zotero plugin for syncing items and notes into Notion

Zotero plugin for fetching number of citations from Google Scholar.

Everything you need to build state-of-the-art foundation multimodal desktop agent, end-to-end.

Building AI agent with hyperpocket tool in a flash

Personal Identifiable Information (PII) entity detection and performance enhancement with synthetic data generation

[NeurIPS'24] Grammar-Aligned Decoding: An algorithm to constrain LLMs' outputs without distorting its original distribution

A repo lists papers related to LLM based agent

A programming framework for agentic AI

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Using tensorflow c api, c++ api, tf lite, tf js, model conversion in Windows

Deep learning in production with Keras, Redis, Flask, and Apache [windows ver.]

Source code for the DEF CON 32 CTF Qualifiers.

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

Implementation of Multi-Game Decision Transformers in PyTorch

Implementation of Trajectory Transformer with attention caching and batched beam search

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"

Bayesian optimisation & Reinforcement Learning library developed by Huawei Noah's Ark Lab

High throughput synchronous and asynchronous reinforcement learning

Online Decision Transformer

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

A collection of reference environments for offline reinforcement learning

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

Code for the paper Fine-Tuning Language Models from Human Preferences