Howard Huang — accepted AI-conference papers

2026

SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video

Howard Huang, Bharath Surianarayanan, Keifer Lee, Chenyu Wang, Chen Feng

ICRA 2026poster

Precise 3D representations of industrial environments enable tasks such as robot localization and digital twin generation. We propose SAVMap, a method for generating a wireframe map of warehouse shelf and light structures using only a panoramic video camera as the sensor input. Sequences of rectifie…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

Wanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-Chin Huang +7

ICLR 2025poster

The development of large language models (LLMs) has been instrumental in advancing state-of-the-art natural language processing applications. Training LLMs with billions of parameters and trillions of tokens requires sophisticated distributed systems that enable composing and comparing several state…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗