Search Results for author:
Found 47 papers, 14 papers with code
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.
Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation
We consider the conditional generation of 3D drug-like molecules with \textit{explicit control} over molecular properties such as drug-like properties (e. g., Quantitative Estimate of Druglikeness or Synthetic Accessibility score) and effectively binding to specific protein sites.
Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories.
Variational methods for Learning Multilevel Genetic Algorithms using the Kantorovich Monad
Levels of selection and multilevel evolutionary processes are essential concepts in evolutionary theory, and yet there is a lack of common mathematical models for these core ideas.
Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models
When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving models' explainability.
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing.
Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos.
Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularization
Recent progresses have been made in object shape generation with generative models such as diffusion models, which increases the shape fidelity.
Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos
This knowledge, sourced from training procedure plans and structured as a directed weighted graph, equips the agent to better navigate the complexities of step sequencing and its potential variations.
Exploring Compositional Visual Generation with Latent Classifier Guidance
We show that this paradigm based on latent classifier guidance is agnostic to pre-trained generative models, and present competitive results for both image generation and sequential manipulation of real and synthetic images.
Conditional Image-to-Video Generation with Latent Flow Diffusion Models
In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.
T-Cell Receptor Optimization with Reinforcement Learning and Mutation Policies for Precesion Immunotherapy
This process is known as TCR recognition and constitutes a key step for immune response.
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning
Source-free domain adaptation (SFDA) is an emerging research topic that studies how to adapt a pretrained source model using unlabeled target data.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Few-Shot Video Classification via Representation Fusion and Promotion Learning
This operation maximizes the contribution of discriminative frames to further capture the similarity of support and query samples from the same category.
Learning Transferable Reward for Query Object Localization with Policy Adaptation
We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set.
AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space.
Dual Projection Generative Adversarial Networks for Conditional Image Generation
We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence.
Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
We evaluate over CATER dataset and find that Hopper achieves 73. 2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames.
Ranked #5 on
Video Object Tracking
on CATER
Disentangled Recurrent Wasserstein Autoencoder
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework.
Analyzing Attention Mechanisms through Lens of Sample Complexity and Loss Landscape
Attention mechanisms have advanced state-of-the-art deep learning models in many machine learning tasks.
Towards Robustness of Deep Neural Networks via Regularization
Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples.
A Deep Generative Model for Molecule Optimization via One Fragment Modification
A pipeline of multiple, identical Modof models is implemented into Modof-pipe to modify an input molecule at multiple disconnection sites.
Ranking-based Convolutional Neural Network Models for Peptide-MHC Binding Prediction
T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e. g., videos and audios) under self-supervision.
Understanding Attention Mechanisms
Attention mechanisms have advanced the state of the art in several machine learning tasks.
Defending Against Adversarial Examples by Regularized Deep Embedding
Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples.
Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
We instead reformulate ZSL as a conditioned visual classification problem, i. e., classifying visual features based on the classifiers learned from the semantic descriptions.
A Deep Spatio-Temporal Fuzzy Neural Network for Passenger Demand Prediction
In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather.
Disentangled Deep Autoencoding Regularization for Robust Image Classification
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations.
Optimal Transport Classifier: Defending Against Adversarial Attacks by Regularized Deep Embedding
Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples.
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols.
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL 2000
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
In this paper, we present a Deep Autoencoding Gaussian Mixture Model (DAGMM) for unsupervised anomaly detection.
On the Use of Word Embeddings Alone to Represent Natural Language Sequences
In this paper, we conduct an extensive comparative study between Simple Word Embeddings-based Models (SWEMs), with no compositional parameters, relative to employing word embeddings within RNN/CNN-based models.
Learning K-way D-dimensional Discrete Code For Compact Embedding Representations
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols.
Convolutional Neural Knowledge Graph Learning
In this paper, we try to learn more complex connections between entities and relationships.
Parametric t-Distributed Stochastic Exemplar-centered Embedding
Parametric embedding methods such as parametric t-SNE (pt-SNE) have been widely adopted for data visualization and out-of-sample data embedding without further computationally expensive optimization or approximation.
Learning Context-Sensitive Convolutional Filters for Text Processing
The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters.
Ranked #13 on
Text Classification
on DBpedia
Exemplar-Centered Supervised Shallow Parametric Data Embedding
Our strategy learns a shallow high-order parametric embedding function and compares training/test data only with learned or precomputed exemplars, resulting in a cost function with linear computational complexity for both training and testing.
A Context-aware Attention Network for Interactive Question Answering
Employing these attention mechanisms, our model accurately understands when it can output an answer or when it requires generating a supplementary question for additional input depending on different contexts.
Adaptive Feature Abstraction for Translating Video to Text
Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features.
A Shallow High-Order Parametric Approach to Data Visualization and Compression
These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations.
Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent
Then we present the study of ISGD batch size to the learning rate, parallelism, synchronization cost, system saturation and scalability.
A Deep Learning Model for Structured Outputs with High-order Interaction
Many real-world applications are associated with structured data, where not only input but also output has interplay.
