Haotian Tang

Research Scientist@Google·美国·OpenReview

研究方向

large language models · visual-language models · 3D deep learning · efficient deep learning · neural architecture search · systems for machine learning

8.5

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

ICLR 2025Oral

6.8

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

ICLR 2025Poster

6.3

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

ICLR 2025Poster

7.0

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

ICLR 2024Oral

三作

5.5

Sparse Refinement for Efficient High-Resolution Semantic Segmentation

合作者 (20)

Haotian Tang

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

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

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

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

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Sparse Refinement for Efficient High-Resolution Semantic Segmentation