Ligeng Zhu

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

FoundationMotion: Auto-labeling and Reasoning about Spatial Movement in Videos

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

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Scaling RL to Long Videos

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

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

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

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Wolf: Accurate Video Captioning with a World Summarization Framework

VILA^2: VLM Augmented VLM with Self-Improvement