Pengxiang Li

SVD_Xtend. Stable Video Diffusion Training Code and Extensions.

TrackDiffusion. [WACV2025] Official PyTorch implementation of TrackDiffusion (https://arxiv.org/abs/2312.00651)

Prophet. Official implementation of "Diffusion Language Models Know the Answer Before Decoding"

OWS. Official Pytorch Implementation of "Outlier-weighed Layerwise Sampling for LLM Fine-tuning" by Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei Liu

ReflectDrive.

DSify. Boosting Driving Scene Understanding with Advanced Vision-Language Models

MixLN. [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxiang Li, Lu Yin, Shiwei Liu

W-CODA2024-Track2. This repository is dedicated to Track 2 of the W-CODA 2024 Workshop, "Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving," held at ECCV 2024.

mini_latent_world_model. DreamerV3 with MetaDrive.

A-CFG.

Spatio-Temporal-Shuffle-Guidance. Python

paper_list_owl.

trackdiff_svd. TrackDiffusion + Stable Video Diffusion

pixeli99.

mmtracking. OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

download_panda_70m. Python

LightZero. [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

GUMP. Generative model for Unified Motion Planning tasks

dreamerv3-torch. Implementation of Dreamer v3 in pytorch.