#
Ir1d
Follow
Starred repositories
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the effective training time by minimizing the downtime due to fa…
Official implementation of Inductive Moment Matching
The Google Scholar PDF Reader browser extension, now with annotations!
Machine Learning Engineering Open Book
Custom implementation of Apple ProRes Log decoding for calibrated iPhone video
Make websites accessible for AI agents
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
GenXD: Generating Any 3D and 4D Scenes. ICLR 2025
(CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings
PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
[ECCV 2024] DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models", Hanwen Liang*, Yuyang Yin*, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N. Plataniotis, Yao Zhao, …
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
Implementation of Nougat Neural Optical Understanding for Academic Documents
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Tools for various online judges. Downloading sample cases, generating additional test cases, testing your code, and submitting it.
An Open-Ended Embodied Agent with Large Language Models
Development repository for the Triton language and compiler
④[ECCV 2024 Oral, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
Official release of the Eyeful Tower dataset, a high-fidelity multi-view capture of 11 real-world scenes, from the paper “VR-NeRF High-Fidelity Virtualized Walkable Spaces” (Xu et al., SIGGRAPH Asi…
