Search Results for author:
Found 33 papers, 15 papers with code
DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
Designing faithful yet accurate AI models is challenging, particularly in the field of individual treatment effect estimation (ITE).
MoST: Multi-modality Scene Tokenization for Motion Prediction
This symbolic representation is a high-level abstraction of the real world, which may render the motion prediction model vulnerable to perception errors (e. g., failures in detecting open-vocabulary obstacles) while missing salient information from the scene context (e. g., poor road conditions).
A General Framework for Portfolio Construction Based on Generative Models of Asset Returns
We consider similarity and optimality measures for value models and employ probability-matching ("blending") and a greedy algorithm ("switching") for policy models.
How to Build an AI Tutor that Can Adapt to Any Course and Provide Accurate Answers Using Large Language Model and Retrieval-Augmented Generation
This paper proposes a low-code solution to build an AI tutor that leverages advanced AI techniques to provide accurate and contextually relevant responses in a personalized learning environment.
WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
To study the effect of these modular approaches, design new paradigms that mitigate these limitations, and accelerate the development of end-to-end motion forecasting models, we augment the Waymo Open Motion Dataset (WOMD) with large-scale, high-quality, diverse LiDAR data for the motion forecasting task.
Measuring Tail Risks
In this paper, we propose a tail risk measure based on the most probable maximum size of risk events (MPMR) that can occur over a length of time.
Covariate-Balancing-Aware Interpretable Deep Learning models for Treatment Effect Estimation
Motivated by the theoretical analysis, we propose a novel objective function for estimating the ATE that uses the energy distance balancing score and hence does not require correct specification of the propensity score model.
MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction
Predicting the future behavior of road users is one of the most challenging and important problems in autonomous driving.
Ranked #16 on
Motion Forecasting
on Argoverse CVPR 2020
Cross-Domain Adaptive Teacher for Object Detection
To mitigate this problem, we propose a teacher-student framework named Adaptive Teacher (AT) which leverages domain adversarial learning and weak-strong data augmentation to address the domain gap.
Adaptive Unbiased Teacher for Cross-Domain Object Detection
This enables the student model to capture domain-invariant features.
Edge of chaos as a guiding principle for modern neural network training
Motivated by the edge of chaos principle behind the optimal performance of neural networks, we study the role of various hyperparameters in modern neural network training algorithms in terms of the order-chaos phase diagram.
Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Interestingly, we show a new equivalence between DP-SGD and DP-SGLD, implying that some non-Bayesian DP training naturally allows for uncertainty quantification.
Video Question Answering with Phrases via Semantic Roles
Video Question Answering (VidQA) evaluation metrics have been limited to a single-word answer or selecting a phrase from a fixed set of phrases.
Unbiased Teacher for Semi-Supervised Object Detection
To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
Spectrum of the doubly charmed molecular pentaquarks in chiral effective field theory
We perform a systematic study on the interactions of the $\Sigma_c^{(*)}D^{(*)}$ systems within the framework of chiral effective field theory.
High Energy Physics - Phenomenology High Energy Physics - Experiment High Energy Physics - Lattice Nuclear Theory
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
When equipped with efficient optimization algorithms, the over-parameterized neural networks have demonstrated high level of performance even though the loss function is non-convex and non-smooth.
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously.
Ranked #5 on
Neural Architecture Search
on ImageNet
CPARR: Category-based Proposal Analysis for Referring Relationships
The task of referring relationships is to localize subject and object entities in an image satisfying a relationship query, which is given in the form of \texttt{<subject, predicate, object>}.
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands.
Ranked #68 on
Neural Architecture Search
on ImageNet
Video Object Grounding using Semantic Roles in Language Description
We explore the task of Video Object Grounding (VOG), which grounds objects in videos referred to in natural language descriptions.
Zero-Shot Grounding of Objects from Natural Language Queries
A phrase grounding system localizes a particular object in an image referred to by a natural language query.
Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
Image-based localization (IBL) aims to estimate the 6DOF camera pose for a given query image.
Billion-scale semi-supervised learning for image classification
This paper presents a study of semi-supervised learning with large convolutional networks.
Ranked #6 on
Image Classification
on OmniBenchmark
(using extra training data)
MAC: Mining Activity Concepts for Language-based Temporal Localization
Previous methods address the problem by considering features from video sliding windows and language queries and learning a subspace to encode their correlation, which ignore rich semantic cues about activities in videos and queries.
CTAP: Complementary Temporal Action Proposal Generation
Temporal action proposal generation is an important task, akin to object proposals, temporal action proposals are intended to capture "clips" or temporal intervals in videos that are likely to contain an action.
Ranked #10 on
Temporal Action Proposal Generation
on ActivityNet-1.3
Motion-Appearance Co-Memory Networks for Video Question Answering
Specifically, there are three salient aspects: (1) a co-memory attention mechanism that utilizes cues from both motion and appearance to generate attention; (2) a temporal conv-deconv network to generate multi-level contextual facts; (3) a dynamic fact ensemble method to construct temporal representation dynamically for different questions.
Ranked #31 on
Visual Question Answering (VQA)
on MSRVTT-QA
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
In this paper, we explore the consistency contained in both visual and language modalities, and leverage complementary external knowledge to facilitate weakly supervised grounding.
Query-guided Regression Network with Context Policy for Phrase Grounding
Given a textual description of an image, phrase grounding localizes objects in the image referred by query phrases in the description.
AMC: Attention guided Multi-modal Correlation Learning for Image Search
According to the intent of query, attention mechanism can be introduced to adaptively balance the importance of different modalities.
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e. g. human actions) segments from untrimmed videos is an important step for large-scale video analysis.
Ranked #8 on
Action Recognition
on THUMOS’14
Knowledge Graph Representation with Jointly Structural and Textual Encoding
In this paper, we propose a novel deep architecture to utilize both structural and textual information of entities.
Learning Word Embeddings from Intrinsic and Extrinsic Views
To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries, Wiki link prediction, and document classification.
ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
ABC-CNN determines an attention map for an image-question pair by convolving the image feature map with configurable convolutional kernels derived from the question's semantics.
