Search Results for author:
Found 36 papers, 11 papers with code
Scalify: scale propagation for efficient low-precision LLM training
Low-precision formats such as float8 have been introduced in machine learning accelerated hardware to improve computational efficiency for large language models training and inference.
MESS: Modern Electronic Structure Simulations
We introduce MESS: a modern electronic structure simulation package implemented in JAX; porting the ESS code to the ML world.
$\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning
In this work, we propose $\texttt{MiniMol}$, a foundational model for molecular learning with 10 million parameters.
Generating QM1B with PySCF$_{\text{IPU}}$
Similar benefits are yet to be unlocked for quantum chemistry, where the potential of deep learning is constrained by comparatively small datasets with 100k to 20M training examples.
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Recently, pre-trained foundation models have enabled significant advancements in multiple fields.
GPS++: Reviving the Art of Message Passing for Molecular Property Prediction
We present GPS++, a hybrid Message Passing Neural Network / Graph Transformer model for molecular property prediction.
Efficient and Sound Differentiable Programming in a Functional Array-Processing Language
Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program.
BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion
We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022.
FLAG: Flow-based 3D Avatar Generation from Sparse Observations
To represent people in mixed reality applications for collaboration and communication, we need to generate realistic and faithful avatar poses.
Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance
We show in this paper that the variation in sequence lengths in common NLP datasets is such that up to 50% of all tokens can be padding.
Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
We introduce an automatic, end-to-end method for recovering the 3D pose and shape of dogs from monocular internet images.
Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
In this paper we introduce the first scalable training technique for 3D generative models from 2D data which utilizes an off-the-shelf non-differentiable renderer.
Creatures great and SMAL: Recovering the shape and motion of animals from video
We present a system to recover the 3D shape and motion of a wide variety of quadrupeds from video.
A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning
However, it is important for the success of algorithmic differentiation that such `simple' objective functions are handled efficiently, as so many problems in computer vision and machine learning are of this form.
Efficient Differentiable Programming in a Functional Array-Processing Language
We present a system for the automatic differentiation of a higher-order functional array-processing language.
Hybrid VAE: Improving Deep Generative Models using Partial Observations
We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing generative models trained on few labeled samples to reach the performance of fully-supervised generative models trained on much larger datasets.
Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading
We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera.
An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models
We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views.
Revisiting the Variable Projection Method for Separable Nonlinear Least Squares Problems
Variable Projection (VarPro) is a framework to solve optimization problems efficiently by optimally eliminating a subset of the unknowns.
On the Two-View Geometry of Unsynchronized Cameras
We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras.
Fits Like a Glove: Rapid and Reliable Hand Shape Personalization
We present a fast, practical method for personalizing a hand shape basis to an individual user's detailed hand shape using only a small set of depth images.
Efficient Intersection of Three Quadrics and Applications in Computer Vision
In this paper, we present a new algorithm for finding all intersections of three quadrics.
Towards Pointless Structure From Motion: 3D Reconstruction and Camera Parameters From General 3D Curves
Modern structure from motion (SfM) remains dependent on point features to recover camera positions, meaning that reconstruction is severely hampered in low-texture environments, for example scanning a plain coffee cup on an uncluttered table.
Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts
Matrix factorization (or low-rank matrix completion) with missing data is a key computation in many computer vision and machine learning tasks, and is also related to a broader class of nonlinear optimization problems such as bundle adjustment.
Reflection Modeling for Passive Stereo
Stereo reconstruction in presence of reality faces many challenges that still need to be addressed.
Efficient Solution to the Epipolar Geometry for Radially Distorted Cameras
In this paper, we present a new efficient solution to this problem that uses 10 image correspondences.
Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations
In this paper, we show how to perform model-based object tracking which allows to reconstruct the object's depth at an order of magnitude higher frame-rate through simple modifications to an off-the-shelf depth camera.
Large-Scale and Drift-Free Surface Reconstruction Using Online Subvolume Registration
Our method supports online model correction, without needing to reprocess or store any input depth data.
Exploiting Uncertainty in Regression Forests for Accurate Camera Relocalization
Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure.
Learning an Efficient Model of Hand Shape Variation From Depth Images
We represent the observed surface using Loop subdivision of a control mesh that is deformed by our learned parametric shape and pose model.
3D Scanning Deformable Objects With a Single RGBD Sensor
We present a 3D scanning system for deformable objects that uses only a single Kinect sensor.
Multi-Output Learning for Camera Relocalization
We formulate this problem as inversion of the generative rendering procedure, i. e., we want to find the camera pose corresponding to a rendering of the 3D scene model that is most similar with the observed input.
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs
As a consequence of our approach, our output is a dense field of 3D rigid body motions, in contrast to the 3D translations that are the norm in scene flow.
User-Specific Hand Modeling from Monocular Depth Sequences
We focus on modeling the human hand, and assume that a single rough template model is available.
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image.
KinectFusion: Real-Time Dense Surface Mapping and Tracking
We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware.
