51 citations · 99 across the 23 of their papers we have counts for
23 papers
How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models
Hongxing Wang, Harenome Razanajato, Zhen Zhang +2
Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear, or recurrent components. We st…
LVSA: Training-Free Sparse Attention for Long Video Diffusion
Gael Glorian, Ioannis Lamprou, Zhen Zhang +2
Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and beyond the training horizon the…
vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models
Peiqi Yin, Jiangyun Zhu, Han Gao +13
Any-to-any multimodal models that jointly handle text, images, video, and audio represent a significant advance in multimodal AI. However, their complex architectures (typically co…
PDEformer-2: A Versatile Foundation Model for Two-Dimensional Partial Differential Equations
Zhanhong Ye, Zining Liu, Bingyang Wu +7
Partial differential equations (PDEs) play a central role in describing many physical phenomena. Various scientific and engineering applications demand a versatile and differentiab…
Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows
Mengtao Yan, Qi Wang, Haining Wang +7
Simulation of fluid flows is crucial for modeling physical phenomena like meteorology, aerodynamics, and biomedicine. Classical numerical solvers often require fine spatiotemporal…
SlotPi: Physics-informed Object-centric Reasoning Models
Jian Li, Wan Han, Ning Lin +8
Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Current…
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
Qi Wang, Yuan Mi, Haoyun Wang +5
Solving partial differential equations (PDEs) by numerical methods meet computational cost challenge for getting the accurate solution since fine grids and small time steps are req…
Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction
Yuan Mi, Pu Ren, Hongteng Xu +6
Data-centric methods have shown great potential in understanding and predicting spatiotemporal dynamics, enabling better design and control of the object system. However, deep lear…
PCNet: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Qi Wang, Pu Ren, Hao Zhou +10
When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergenc…
PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems
Bocheng Zeng, Qi Wang, Mengtao Yan +6
Solving partial differential equations (PDEs) serves as a cornerstone for modeling complex dynamical systems. Recent progresses have demonstrated grand benefits of data-driven neur…
PDEformer-1: A Foundation Model for One-Dimensional Partial Differential Equations
Zhanhong Ye, Xiang Huang, Leheng Chen +5
This paper introduces PDEformer-1, a versatile neural solver capable of simultaneously addressing various partial differential equations (PDEs). With the PDE represented as a compu…
PDEformer: Towards a Foundation Model for One-Dimensional Partial Differential Equations
Zhanhong Ye, Xiang Huang, Leheng Chen +3
This paper introduces PDEformer, a neural solver for partial differential equations (PDEs) capable of simultaneously addressing various types of PDEs. We propose to represent the P…
Learning to simulate partially known spatio-temporal dynamics with trainable difference operators
Xiang Huang, Zhuoyuan Li, Hongsheng Liu +4
Recently, using neural networks to simulate spatio-temporal dynamics has received a lot of attention. However, most existing methods adopt pure data-driven black-box models, which…
Deep learning-based reduced order model for three-dimensional unsteady flow using mesh transformation and stitching
Xin Li, Zhiwen Deng, Rui Feng +4
Artificial intelligence-based three-dimensional(3D) fluid modeling has gained significant attention in recent years. However, the accuracy of such models is often limited by the pr…
Analysis of the Decoder Width for Parametric Partial Differential Equations
Zhanhong Ye, Hongsheng Liu, Zidong Wang +1
Recently, Meta-Auto-Decoder (MAD) was proposed as a novel reduced order model (ROM) for solving parametric partial differential equations (PDEs), and the best possible performance…
Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies
Zhiwen Deng, Jing Wang, Hongsheng Liu +7
The Reynolds-averaged Navier-Stokes equation for compressible flow over supercritical airfoils under various flow conditions must be rapidly and accurately solved to shorten design…
Solving Boltzmann equation with neural sparse representation
Zhengyi Li, Yanli Wang, Hongsheng Liu +2
We consider the neural sparse representation to solve Boltzmann equation with BGK and quadratic collision model, where a network-based ansatz that can approximate the distribution…
Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Differential Equations
Zhanhong Ye, Xiang Huang, Hongsheng Liu +1
Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i.e., PDEs with different physical parameters, bo…
StepDIRECT -- A Derivative-Free Optimization Method for Stepwise Functions
Dzung T. Phan, Hongsheng Liu, Lam M. Nguyen
In this paper, we propose the StepDIRECT algorithm for derivative-free optimization (DFO), in which the black-box objective function has a stepwise landscape. Our framework is base…
Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks
Xiang Huang, Hongsheng Liu, Beiji Shi +11
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a pro…
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Xiang Huang, Zhanhong Ye, Hongsheng Liu +11
Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i.e., PDEs with different physical parameters, bo…
Statistical inference for piecewise normal distributions and stochastic variational inequalities
Shu Lu, Hongsheng Liu
In this paper we first provide a method to compute confidence intervals for the center of a piecewise normal distribution given a sample from this distribution, under certain assum…
Convergence of the Augmented Decomposition Algorithm
Hongsheng Liu, Shu Lu
We study the convergence of the Augmented Decomposition Algorithm (ADA) proposed in [32] for solving multi-block separable convex minimization problems subject to linear constraint…