Search Results for author:
Found 33 papers, 17 papers with code
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis, even in challenging settings such as driving scenes and monocular dynamic video.
A Radiance Field Loss for Fast and Simple Emissive Surface Reconstruction
Building on existing emissive volume reconstruction algorithms, we introduce a subtle yet impactful modification of the loss function requiring changes to only a few lines of code: instead of integrating the radiance field along rays and supervising the resulting images, we project the training images into the scene to directly supervise the spatio-directional radiance field.
Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators
Our experiments across a series of LLMs indicate that trained hidden-state probes provide the most reliable confidence estimates, albeit at the expense of requiring access to weights and training data.
Labeled Morphological Segmentation with Semi-Markov Models
We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks.
Compact Neural Graphics Primitives with Learned Hash Probing
Neural graphics primitives are faster and achieve higher quality when their neural networks are augmented by spatial data structures that hold trainable features arranged in a grid.
Adaptive Shells for Efficient Neural Radiance Field Rendering
We then extract an explicit mesh of a narrow band around the surface, with width determined by the kernel size, and fine-tune the radiance field within this band.
Neuralangelo: High-Fidelity Neural Surface Reconstruction
Neural surface reconstruction has been shown to be powerful for recovering dense 3D surfaces via image-based neural rendering.
Towards interpretable quantum machine learning via single-photon quantum walks
Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits.
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene.
Variable Bitrate Neural Fields
Neural approximations of scalar and vector fields, such as signed distance functions and radiance fields, have emerged as accurate, high-quality representations.
RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis
We present a large-scale synthetic dataset for novel view synthesis consisting of ~300k images rendered from nearly 2000 complex scenes using high-quality ray tracing at high resolution (1600 x 1600 pixels).
Ranked #1 on
Novel View Synthesis
on RTMV
Zero and Few-shot Learning for Author Profiling
We find that entailment-based models out-perform supervised text classifiers based on roberta-XLM and that we can reach 80% of the accuracy of previous approaches using less than 50\% of the training data on average.
Active Few-Shot Learning with FASL
Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks.
Few-Shot Learning with Siamese Networks and Label Tuning
We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification.
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
Path Guiding Using Spatio-Directional Mixture Models
In particular, we approximate incident radiance as an online-trained $5$D mixture that is accelerated by a $k$D-tree.
Extracting Triangular 3D Models, Materials, and Lighting From Images
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
Ranked #2 on
Depth Prediction
on Stanford-ORB
MATE: Multi-view Attention for Table Transformer Efficiency
However, more than 20% of relational tables on the web have 20 or more rows (Cafarella et al., 2008), and these large tables present a challenge for current Transformer models, which are typically limited to 512 tokens.
Ranked #2 on
Question Answering
on HybridQA
Real-time Neural Radiance Caching for Path Tracing
Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i. e. we opt for training the radiance cache while rendering.
DoT: An efficient Double Transformer for NLP tasks with tables
To improve efficiency while maintaining a high accuracy, we propose a new architecture, DoT, a double transformer model, that decomposes the problem into two sub-tasks: A shallow pruning transformer that selects the top-K tokens, followed by a deep task-specific transformer that takes as input those K tokens.
TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training
We adopt the binary TAPAS model of Eisenschlos et al. (2020) to this task.
Open Domain Question Answering over Tables via Dense Retrieval
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages.
Collective defense of honeybee colonies: experimental results and theoretical modeling
Social insect colonies routinely face large vertebrate predators, against which they need to mount a collective defense.
Understanding tables with intermediate pre-training
To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy.
Ranked #11 on
Table-based Fact Verification
on TabFact
Neural Control Variates
We propose neural control variates (NCV) for unbiased variance reduction in parametric Monte Carlo integration.
TAPAS: Weakly Supervised Table Parsing via Pre-training
In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms.
Ranked #1 on
Semantic Parsing
on SQA
(Accuracy metric)
Development of swarm behavior in artificial learning agents that adapt to different foraging environments
Collective behavior, and swarm formation in particular, has been studied from several perspectives within a large variety of fields, ranging from biology to physics.
How a minimal learning agent can infer the existence of unobserved variables in a complex environment
According to a mainstream position in contemporary cognitive science and philosophy, the use of abstract compositional concepts is both a necessary and a sufficient condition for the presence of genuine thought.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Answering Conversational Questions on Structured Data without Logical Forms
We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation.
Neural Importance Sampling
We propose to use deep neural networks for generating samples in Monte Carlo integration.
Modelling collective motion based on the principle of agency
Collective motion is an intriguing phenomenon, especially considering that it arises from a set of simple rules governing local interactions between individuals.
Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks
To render a new scene, we sample visible points of the cloud and, for each, extract a hierarchical 3D descriptor of the cloud geometry with respect to the shading location and the light source.
