59 citations · 185 across the 20 of their papers we have counts for
21 papers
SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference
Hongliang Cao, Xiuyu Li, Siqi Wang +3
Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D) expert transfers enter the c…
: Unifying Generation and Self-Verification for Parallel Reasoners
Harman Singh, Xiuyu Li, Kusha Sareen +14
Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in…
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
Samir Khaki, Xiuyu Li, Junxian Guo +7
Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and…
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao +10
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens…
Learning Adaptive Parallel Reasoning with Language Models
Jiayi Pan, Xiuyu Li, Long Lian +6
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chai…
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Haocheng Xi, Shuo Yang, Yilong Zhao +11
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a…
NVILA: Efficient Frontier Visual Language Models
Zhijian Liu, Ligeng Zhu, Baifeng Shi +24
Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a…
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Muyang Li, Yujun Lin, Zhekai Zhang +7
Diffusion models can effectively generate high-quality images. However, as they scale, rising memory demands and higher latency pose substantial deployment challenges. In this work…
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…
LLoCO: Learning Long Contexts Offline
Sijun Tan, Xiuyu Li, Shishir Patil +5
Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substan…
Magic-Me: Identity-Specific Video Customized Diffusion
Ze Ma, Daquan Zhou, Chun-Hsiao Yeh +6
Creating content with specified identities (ID) has attracted significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven…
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…
CVPR 2023 Text Guided Video Editing Competition
Jay Zhangjie Wu, Xiuyu Li, Difei Gao +17
Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing…
SqueezeLLM: Dense-and-Sparse Quantization
Sehoon Kim, Coleman Hooper, Amir Gholami +5
Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challen…
Q-Diffusion: Quantizing Diffusion Models
Xiuyu Li, Yijiang Liu, Long Lian +5
Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption,…
Data Isotopes for Data Provenance in DNNs
Emily Wenger, Xiuyu Li, Ben Y. Zhao +1
Today, creators of data-hungry deep neural networks (DNNs) scour the Internet for training fodder, leaving users with little control over or knowledge of when their data is appropr…
The ArtBench Dataset: Benchmarking Generative Models with Artworks
Peiyuan Liao, Xiuyu Li, Xihui Liu +1
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation. It comprises 60,000 images of art…
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…
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Chenhui Deng, Xiuyu Li, Zhuo Feng +1
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnera…
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Derek Lim, Felix Hohne, Xiuyu Li +4
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networ…
New Benchmarks for Learning on Non-Homophilous Graphs
Derek Lim, Xiuyu Li, Felix Hohne +1
Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute. As such, ubiquitous datase…