Search Results for author:
Found 27 papers, 14 papers with code
Document-level Neural MT: A Systematic Comparison
In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions.
Simple linear attention language models balance the recall-throughput tradeoff
In this work, we explore whether we can improve language model efficiency (e. g. by reducing memory consumption) without compromising on recall.
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
Experiments show Hedgehog recovers over 99% of standard Transformer quality in train-from-scratch and finetuned-conversion settings, outperforming prior linear attentions up to 6 perplexity points on WikiText-103 with causal GPTs, and up to 8. 7 GLUE score points on finetuned bidirectional BERTs.
Enabling CMF Estimation in Data-Constrained Scenarios: A Semantic-Encoding Knowledge Mining Model
This new data-driven framework provides a cost-effective and adaptable solution that complements the case-specific approaches for CMF estimation, which is particularly beneficial when availability of crash data or time imposes constraints.
Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning
In this paper, we propose a joint optimization approach for traffic signal control and vehicle routing in signalized road networks.
EVKG: An Interlinked and Interoperable Electric Vehicle Knowledge Graph for Smart Transportation System
Over the past decade, the electric vehicle industry has experienced unprecedented growth and diversification, resulting in a complex ecosystem.
Effectively Modeling Time Series with Simple Discrete State Spaces
For expressivity, we propose a new SSM parameterization based on the companion matrix -- a canonical representation for discrete-time processes -- which enables SpaceTime's SSM layers to learn desirable autoregressive processes.
Simple Hardware-Efficient Long Convolutions for Sequence Modeling
We find that a key requirement to achieving high performance is keeping the convolution kernels smooth.
Contrastive Adapters for Foundation Model Group Robustness
We also find that efficient ways to improve model inference (e. g., via adapters, lightweight networks with FM embeddings as inputs) do not consistently improve and can sometimes hurt group robustness compared to zero-shot (e. g., increasing the accuracy gap by 50. 1 pp on CelebA).
Deep Learning and Symbolic Regression for Discovering Parametric Equations
Symbolic regression is a machine learning technique that can learn the governing formulas of data and thus has the potential to transform scientific discovery.
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
We first prove that adding a weighted class-conditional InfoNCE loss to SupCon controls the degree of spread.
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Despite the black-box nature of foundation models, we prove results characterizing how our approach improves performance and show that lift scales with the smoothness of label distributions in embedding space.
Triangle and Four Cycle Counting with Predictions in Graph Streams
We propose data-driven one-pass streaming algorithms for estimating the number of triangles and four cycles, two fundamental problems in graph analytics that are widely studied in the graph data stream literature.
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
As ERM models can be good spurious attribute predictors, CNC works by (1) using a trained ERM model's outputs to identify samples with the same class but dissimilar spurious features, and (2) training a robust model with contrastive learning to learn similar representations for same-class samples.
The Details Matter: Preventing Class Collapse in Supervised Contrastive Learning
Supervised contrastive learning optimizes a loss that pushes together embeddings of points from the same class while pulling apart embeddings of points from different classes.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Personalized Federated Learning with First Order Model Optimization
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients.
Using Computer Vision to Automate Hand Detection and Tracking of Surgeon Movements in Videos of Open Surgery
A state-of-the-art convolutional neural network architecture for object detection was used to detect operating hands in open surgery videos.
Characterizing Policy Divergence for Personalized Meta-Reinforcement Learning
Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.
PLATON II: New Capabilities And A Comprehensive Retrieval on HD 189733b Transit and Eclipse Data
Recently, we introduced PLanetary Atmospheric Tool for Observer Noobs (PLATON), a Python package that calculates model transmission spectra for exoplanets and retrieves atmospheric characteristics based on observed spectra.
Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics
Deciphering hierarchical organization of topologically associated domains through change-point testing
Background: The nucleus of eukaryotic cells spatially packages chromosomes into a hierarchical and distinct segregation that plays critical roles in maintaining transcription regulation.
Applications Methodology
Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes
However, capturing the short-term effects of drugs and therapeutic interventions on patient physiological state remains challenging.
Forward modelling and retrievals with PLATON, a fast open source tool
It also has less commonly included features, such as a Mie scattering cloud model and unocculted starspot corrections.
Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics
Deep Weighted Averaging Classifiers
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text.
Detection of a Westward Hotspot Offset in the Atmosphere of a Hot Gas Giant CoRoT-2b
The peculiar infrared flux map of CoRoT-2b may result from westward winds due to non-synchronous rotation magnetic effects, or partial cloud coverage, that obscures the emergent flux from the planet's eastern hemisphere.
Earth and Planetary Astrophysics
Reverse Curriculum Generation for Reinforcement Learning
The robot is trained in reverse, gradually learning to reach the goal from a set of start states increasingly far from the goal.
Probabilistically Safe Policy Transfer
Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy.
