xuanlinli17

CS285_Fa19_Deep_Reinforcement_Learning

My solutions to UC Berkeley CS285 (originally CS294-112, deeprlcourse) Fall 2019 assignments

large_vlm_distillation_ood

Distilling Large Vision-Language Model with Out-of-Distribution Generalizability (ICCV 2023)

corl_22_frame_mining

[CoRL22] Frame Mining - a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds

iclr2021_rlreg

Regularization Matters in Policy Optimization

autoregressive_inference

Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)

xuanlinli17.github.io

MinkowskiEngine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

python-pcl

Python bindings to the pointcloud library (pcl)

activezero2_official

efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

graspnetAPI

Toolbox for our GraspNet-1Billion dataset.

instant-nsr-pl

Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ml-veclip

The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"

MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

MobileVLM

Strong and Open Vision Language Assistant for Mobile Devices

nanoowl

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

rlds_dataset_builder

ManiSkill2 RLDS dataset builder for X-embodiment dataset conversion.

robotics_transformer

tapnet

Tracking Any Point (TAP)

tensor2robot

Distributed machine learning infrastructure for large-scale robotics research

TensoRF

[ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

XMem

XMem_fork

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection