Related papers: Rose: Composable Autodiff for the Interactive Web
Reduced-order models that accurately abstract high fidelity models and enable faster simulation is vital for real-time, model-based diagnosis applications. In this paper, we outline a novel hybrid modeling approach that combines machine…
Personalized interior decoration design often incurs high labor costs. Recent efforts in developing intelligent interior design systems have focused on generating textual requirement-based decoration designs while neglecting the problem of…
Autodiff refers to the core of the automatic differentiation systems developed in projects like JAX and Dex. Autodiff has recently been formalised in a linear typed calculus by Radul et al in arXiv:2204.10923. Although this formalisation…
Wireless communications are nowadays shifting to higher operation frequencies with the aim to meet the ever-increasing demand for bandwidth. While reconfigurable intelligent surfaces (RISs) are usually envisioned to restore the…
Many engineering problems involve learning hidden dynamics from indirect observations, where the physical processes are described by systems of partial differential equations (PDE). Gradient-based optimization methods are considered…
Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pretrained diffusion models can be reused…
Reconfigurable intelligent surface (RIS)-aided networks have been investigated for the purpose of improving the system performance. However, the introduced unit modulus phase shifts and coupling characteristic bring enormous challenges to…
The adoption of a Reconfigurable Intelligent Surface (RIS) for downlink multi-user communication from a multi-antenna base station is investigated in this paper. We develop energy-efficient designs for both the transmit power allocation and…
We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations into structured robot states-such as 3D keypoints or joint…
Reconfigurable intelligent surface (RIS) provides a promising way to build the programmable wireless transmission environments in the future. Owing to the large number of reflecting elements used at the RIS, joint optimization for the…
Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework…
Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as…
We present a simple yet powerful framework for solving inverse problems by leveraging automatic differentiation. Our method is broadly applicable whenever a smooth cost function can be defined near the true solution, and a numerical…
We present jax-cosmo, a library for automatically differentiable cosmological theory calculations. It uses the JAX library, which has created a new coding ecosystem, especially in probabilistic programming. As well as batch acceleration,…
Deep learning (DL) has revolutionized many fields such as materials design and protein folding. Recent studies have demonstrated the advantages of DL in the inverse design of structural colors, by effectively learning the complex nonlinear…
User mobility trajectory and mobile traffic data are essential for a wide spectrum of applications including urban planning, network optimization, and emergency management. However, large-scale and fine-grained mobility data remains…
Metasurface inverse design has become central to realizing complex optical functionality, yet translating target responses into executable, solver-compatible workflows still demands specialized expertise in computational electromagnetics…
Accurate and high-fidelity driving scene reconstruction relies on fully leveraging scene information as conditioning. However, existing approaches, which primarily use 3D bounding boxes and binary maps for foreground and background control,…
Background foreground separation (BFS) is a popular computer vision problem where dynamic foreground objects are separated from the static background of a scene. Typically, this is performed using consumer cameras because of their low cost,…
This paper introduces a real-time algorithm for navigating complex unknown environments cluttered with movable obstacles. Our algorithm achieves fast, adaptable routing by actively attempting to manipulate obstacles during path planning and…