333 citations · 857 across the 22 of their papers we have counts for
22 papers
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Shang Yang, Junxian Guo, Haotian Tang +7
Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due…
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Enze Xie, Junsong Chen, Junyu Chen +8
We introduce Sana, a text-to-image framework that can efficiently generate images up to 40964096 resolution. Sana can synthesize high-resolution, high-quality images with s…
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Guangxuan Xiao, Jiaming Tang, Jingwei Zuo +5
Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attenti…
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Haotian Tang, Yecheng Wu, Shang Yang +7
We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in…
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Junyu Chen, Han Cai, Junsong Chen +6
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated…
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Yecheng Wu, Zhuoyang Zhang, Junyu Chen +9
VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for underst…
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Yukang Chen, Fuzhao Xue, Dacheng Li +15
Long-context capability is critical for multi-modal foundation models, especially for long video understanding. We introduce LongVILA, a full-stack solution for long-context visual…
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
Zhijian Liu, Zhuoyang Zhang, Samir Khaki +5
Semantic segmentation empowers numerous real-world applications, such as autonomous driving and augmented/mixed reality. These applications often operate on high-resolution images…
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Yujun Lin, Haotian Tang, Shang Yang +4
Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. N…
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
Haotian Tang, Shang Yang, Zhijian Liu +6
Sparse convolution plays a pivotal role in emerging workloads, including point cloud processing in AR/VR, autonomous driving, and graph understanding in recommendation systems. Sin…
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Yukang Chen, Shengju Qian, Haotian Tang +4
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, trainin…
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Ji Lin, Jiaming Tang, Haotian Tang +7
Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud…
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
Xuanyao Chen, Zhijian Liu, Haotian Tang +3
High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hind…
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Zhijian Liu, Xinyu Yang, Haotian Tang +2
Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on p…
End-to-End Entity Detection with Proposer and Regressor
Xueru Wen, Changjiang Zhou, Haotian Tang +3
Named entity recognition is a traditional task in natural language processing. In particular, nested entity recognition receives extensive attention for the widespread existence of…
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Zhijian Liu, Haotian Tang, Alexander Amini +4
Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with ca…
PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
Zhijian Liu, Haotian Tang, Shengyu Zhao +2
3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resour…
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
Han Cai, Ji Lin, Yujun Lin +5
Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech reco…
TorchSparse: Efficient Point Cloud Inference Engine
Haotian Tang, Zhijian Liu, Xiuyu Li +2
Deep learning on point clouds has received increased attention thanks to its wide applications in AR/VR and autonomous driving. These applications require low latency and high accu…
PointAcc: Efficient Point Cloud Accelerator
Yujun Lin, Zhekai Zhang, Haotian Tang +2
Deep learning on point clouds plays a vital role in a wide range of applications such as autonomous driving and AR/VR. These applications interact with people in real-time on edge…
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Haotian Tang, Zhijian Liu, Shengyu Zhao +4
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able…
Point-Voxel CNN for Efficient 3D Deep Learning
Zhijian Liu, Haotian Tang, Yujun Lin +1
We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches…