Search Results for author:
Found 23 papers, 14 papers with code
Humanity's Last Exam
However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities.
Ranked #4 on
Humanity's Last Exam
on Humanity's Last Exam
LocateBench: Evaluating the Locating Ability of Vision Language Models
The ability to locate an object in an image according to natural language instructions is crucial for many real-world applications.
RelBench: A Benchmark for Deep Learning on Relational Databases
We use RelBench to conduct the first comprehensive study of Relational Deep Learning (RDL) (Fey et al., 2024), which combines graph neural network predictive models with (deep) tabular models that extract initial entity-level representations from raw tables.
Relational Deep Learning: Graph Representation Learning on Relational Databases
The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links.
Expressive Sign Equivariant Networks for Spectral Geometric Learning
In this work, we demonstrate the benefits of sign equivariance for these tasks.
On Retrieval Augmentation and the Limitations of Language Model Training
Augmenting a language model (LM) with $k$-nearest neighbors ($k$NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain elusive.
On the Stability of Expressive Positional Encodings for Graphs
Despite many attempts to address non-uniqueness, most methods overlook stability, leading to poor generalization on unseen graph structures.
Molecular Property Prediction
Out-of-Distribution Generalization
+1
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
Specifically, in the contrastive learning setting, we introduce an equivariance objective and theoretically prove that its minima forces augmentations on input space to correspond to rotations on the spherical embedding space.
A deep learning approach to using wearable seismocardiography (SCG) for diagnosing aortic valve stenosis and predicting aortic hemodynamics obtained by 4D flow MRI
We also investigated the ability of this deep learning technique to differentiate between patients diagnosed with aortic valve stenosis (AS), non-AS patients with a bicuspid aortic valve (BAV), non-AS patients with a mechanical aortic valve (MAV), and healthy subjects with a normal tricuspid aortic valve (TAV).
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations
Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models.
Leveraging Large Language Models for Multiple Choice Question Answering
A more natural prompting approach is to present the question and answer options to the LLM jointly and have it output the symbol (e. g., "A") associated with its chosen answer option.
Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
Integrating functions on discrete domains into neural networks is key to developing their capability to reason about discrete objects.
Combinatorial Optimization
Vocal Bursts Intensity Prediction
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks.
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors.
Ranked #6 on
Graph Regression
on ZINC-full
Can contrastive learning avoid shortcut solutions?
However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i. e., by inadvertently suppressing important predictive features.
A Matrix Autoencoder Framework to Align the Functional and Structural Connectivity Manifolds as Guided by Behavioral Phenotypes
We propose a novel matrix autoencoder to map functional connectomes from resting state fMRI (rs-fMRI) to structural connectomes from Diffusion Tensor Imaging (DTI), as guided by subject-level phenotypic measures.
Contrastive Learning with Hard Negative Samples
How can you sample good negative examples for contrastive learning?
Deep sr-DDL: Deep Structurally Regularized Dynamic Dictionary Learning to Integrate Multimodal and Dynamic Functional Connectomics data for Multidimensional Clinical Characterizations
The generative component is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying subject-specific loadings.
A Deep-Generative Hybrid Model to Integrate Multimodal and Dynamic Connectivity for Predicting Spectrum-Level Deficits in Autism
The generative part of our framework is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying patient-specific loadings.
Debiased Contrastive Learning
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples.
Strength from Weakness: Fast Learning Using Weak Supervision
Our theoretical results are reflected empirically across a range of tasks and illustrate how weak labels speed up learning on the strong task.
Perceptual Regularization: Visualizing and Learning Generalizable Representations
We propose a technique termed perceptual regularization that enables both visualization of the latent representation and control over the generality of the learned representation.
Flexible Modeling of Diversity with Strongly Log-Concave Distributions
We propose SLC as the right extension of SR that enables easier, more intuitive control over diversity, illustrating this via examples of practical importance.
