Search Results for author:
Found 32 papers, 10 papers with code
Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings.
Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective
In contrast, the Warmup-Stable-Decay (WSD) schedule uses a constant learning rate to produce a main branch of iterates that can in principle continue indefinitely without a pre-specified compute budget.
Object Registration in Neural Fields
Neural fields provide a continuous scene representation of 3D geometry and appearance in a way which has great promise for robotics applications.
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks.
Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields
Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene.
Anticipatory Music Transformer
We achieve this by interleaving sequences of events and controls, such that controls appear following stopping times in the event sequence.
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training.
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM).
Retrospectives on the Embodied AI Workshop
We present a retrospective on the state of Embodied AI research.
FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators
Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe.
FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor.
Reducing the Athena WFI charged particle background: Results from Geant4 simulations
One of the science goals of the Wide Field Imager (WFI) on ESA's Athena X-ray observatory is to map hot gas structures in the universe, such as clusters and groups of galaxies and the intergalactic medium.
Instrumentation and Methods for Astrophysics
A simulation environment for drone cinematography
Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface.
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
BenchBot: Evaluating Robotics Research in Photorealistic 3D Simulation and on Real Robots
We introduce BenchBot, a novel software suite for benchmarking the performance of robotics research across both photorealistic 3D simulations and real robot platforms.
Robotics
Tropical and Extratropical Cyclone Detection Using Deep Learning
All four U-Nets are fast information extraction tools and perform with a ROI detection accuracy ranging from 80% to 99%.
What can robotics research learn from computer vision research?
The computer vision and robotics research communities are each strong.
From Google Maps to a Fine-Grained Catalog of Street trees
We believe this is the first work to exploit publicly available image data for fine-grained tree mapping at city-scale, respectively over many thousands of trees.
The Probabilistic Object Detection Challenge
We introduce a new challenge for computer and robotic vision, the first ACRV Robotic Vision Challenge, Probabilistic Object Detection.
Probabilistic Object Detection: Definition and Evaluation
We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections.
A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management
In this work, we obviate this assumption and introduce a rapidly deployable approach able to operate on any field without any weed species assumptions prior to deployment.
Towards Unsupervised Weed Scouting for Agricultural Robotics
This greatly limits deployability as classification systems must be retrained for any field with a different set of weed species present within them.
Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees
The main technical challenge is combining test time information from multiple views of each geographic location (e. g., aerial and street views).
Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art
This dataset is designed to train and test algorithms for fine-grained categorisation of people, it is also useful for benchmarking tracking, detection and pose estimation of pedestrians.
From Categories to Individuals in Real Time -- A Unified Boosting Approach
A method for online, real-time learning of individual-object detectors is presented.
An improved model of Charge Transfer Inefficiency and correction algorithm for the Hubble Space Telescope
Read noise is added after charge transfer so does not get trailed - but it is incorrectly untrailed during post-processing.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics
