Violet Xiang's repositories
EmergentSocialDynamics
Context dependent intrinsic motivation allows diverse social dynamics to emerge from different environment.
a-PyTorch-Tutorial-to-Image-Captioning
Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
alignment
ELIGN: Expectation Alignment as a Multi-agent Intrinsic Reward
arxiv-style
A Latex style and template for paper preprints (based on NIPS style)
crafter
Benchmarking the Spectrum of Agent Capabilities
DeepGaze
pytorch implementation of the different DeepGaze models
FA20_PSYCH251
Class repo for PSYCH251
FixaTons
A collection of Human Fixations Datasets and Metrics for Scanpath Similarity
gpu-monitor
Script to remotely check GPU servers for free GPUs
magnebot
High-level API for the TDW Magnebot
Melting-Pot-Contest-2023
Fork for melting-pot challenge
meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
multiagent-particle-envs
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
OpenSelfSup
Self-Supervised Learning Toolbox and Benchmark
OvercookedGPT
An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic multi-agent settings.
problem_sets
Problem sets
PSYCH209FinalProject
Understanding language's effect on visual representation
rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
sample-model-submission
Template and examples for model submissions to Brain-Score
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
SoM
Set-of-Mark Prompting for LMMs
violetxi.github.io
Personal website
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs