Picture for Ligeng Zhu

Ligeng Zhu

NVILA: Efficient Frontier Visual Language Models

Add code
Dec 05, 2024
Viaarxiv icon

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Add code
Oct 25, 2024
Figure 1 for COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Figure 2 for COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Figure 3 for COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Figure 4 for COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Viaarxiv icon

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

Add code
Oct 15, 2024
Viaarxiv icon

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Add code
Sep 06, 2024
Figure 1 for VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Figure 2 for VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Figure 3 for VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Figure 4 for VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Viaarxiv icon

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Add code
Aug 21, 2024
Figure 1 for LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Figure 2 for LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Figure 3 for LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Figure 4 for LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Viaarxiv icon

Wolf: Captioning Everything with a World Summarization Framework

Add code
Jul 26, 2024
Figure 1 for Wolf: Captioning Everything with a World Summarization Framework
Figure 2 for Wolf: Captioning Everything with a World Summarization Framework
Figure 3 for Wolf: Captioning Everything with a World Summarization Framework
Figure 4 for Wolf: Captioning Everything with a World Summarization Framework
Viaarxiv icon

$VILA^2$: VILA Augmented VILA

Add code
Jul 24, 2024
Viaarxiv icon

Tiny Machine Learning: Progress and Futures

Add code
Mar 29, 2024
Viaarxiv icon

PockEngine: Sparse and Efficient Fine-tuning in a Pocket

Add code
Oct 26, 2023
Viaarxiv icon

On-Device Training Under 256KB Memory

Add code
Jul 14, 2022
Figure 1 for On-Device Training Under 256KB Memory
Figure 2 for On-Device Training Under 256KB Memory
Figure 3 for On-Device Training Under 256KB Memory
Figure 4 for On-Device Training Under 256KB Memory
Viaarxiv icon