Search Results for author:
Found 89 papers, 51 papers with code
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems.
Zero-shot Object-Level OOD Detection with Context-Aware Inpainting
RONIN conditions the inpainting process with the predicted ID label, drawing the input object closer to the in-distribution domain.
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
This paper addresses the prevalent issue of label shift in an online setting with missing labels, where data distributions change over time and obtaining timely labels is challenging.
Correction with Backtracking Reduces Hallucination in Summarization
The results show that CoBa is effective and efficient in reducing hallucination, and offers great adaptability and flexibility.
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train.
Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
Additionally, we leverage the statistics for a novel self-training process to stabilize the training.
On the Effectiveness of Offline RL for Dialogue Response Generation
A common training technique for language models is teacher forcing (TF).
IncDSI: Incrementally Updatable Document Retrieval
Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents.
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts.
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting
We present a novel approach for this task - Lift, Map, Detect (LMD) - that leverages recent advancement in diffusion models.
Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction
Are multimodal inputs necessary for grammar induction?
Latent Diffusion for Language Generation
We then demonstrate that continuous diffusion models can be learned in the latent space of the language autoencoder, enabling us to sample continuous latent representations that can be decoded into natural language with the pretrained decoder.
Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning
Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy.
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions.
Differentially Private Multi-Party Data Release for Linear Regression
Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects.
Long-term Control for Dialogue Generation: Methods and Evaluation
This setting requires a model to not only consider the generation of these control words in the immediate context, but also produce utterances that will encourage the generation of the words at some time in the (possibly distant) future.
Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data.
Ranked #3 on
Named Entity Recognition (NER)
on SLUE
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data.
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely.
Does Label Differential Privacy Prevent Label Inference Attacks?
Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels.
Language-driven Semantic Segmentation
We present LSeg, a novel model for language-driven semantic image segmentation.
Ranked #1 on
Few-Shot Semantic Segmentation
on FSS-1000
Machine learning discovery of new phases in programmable quantum simulator snapshots
Specifically, we apply Hybrid-CCNN to analyze new quantum phases on square lattices with programmable interactions.
Is High Variance Unavoidable in RL? A Case Study in Continuous Control
In this paper, we investigate causes for this perceived instability.
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition
This paper is a study of performance-efficiency trade-offs in pre-trained models for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Online Adaptation to Label Distribution Shift
Machine learning models often encounter distribution shifts when deployed in the real world.
Towards Deeper Deep Reinforcement Learning with Spectral Normalization
In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern networks with skip connections and normalization, focusing specifically on actor-critic algorithms.
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning.
Making Paper Reviewing Robust to Bid Manipulation Attacks
We develop a novel approach for paper bidding and assignment that is much more robust against such attacks.
Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
Machine learning models are a powerful theoretical tool for analyzing data from quantum simulators, in which results of experiments are sets of snapshots of many-body states.
Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation
To integrate the strengths of the two classifiers, we apply the well-established co-training framework, in which the two classifiers exchange their high confident predictions to iteratively "teach each other" so that both classifiers can excel in the target domain.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Wasserstein Distances for Stereo Disparity Estimation
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values.
Ranked #2 on
Stereo Depth Estimation
on KITTI2015
(three pixel error metric)
3D Object Detection From Stereo Images
Autonomous Driving
+5
Revisiting Few-sample BERT Fine-tuning
We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instability of the process.
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike.
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
Reliable and accurate 3D object detection is a necessity for safe autonomous driving.
On Feature Normalization and Data Augmentation
The moments (a. k. a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training time.
Ranked #32 on
Domain Generalization
on ImageNet-A
On Hiding Neural Networks Inside Neural Networks
Modern neural networks often contain significantly more parameters than the size of their training data.
Revisiting Meta-Learning as Supervised Learning
Recent years have witnessed an abundance of new publications and approaches on meta-learning.
Identifying Mislabeled Data using the Area Under the Margin Ranking
Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled.
Convolutional Networks with Dense Connectivity
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
TrojanNet: Exposing the Danger of Trojan Horse Attack on Neural Networks
The complexity of large-scale neural networks can lead to poor understanding of their internal details.
SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples.
LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
We obtain 2-D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3-D lidar point cloud by building a graph of connections among 3-D points and 2-D pixels.
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images.
Integrated Triaging for Fast Reading Comprehension
This paper introduces Integrated Triaging, a framework that prunes almost all context in early layers of a network, leaving the remaining (deep) layers to scan only a tiny fraction of the full corpus.
Detecting Noisy Training Data with Loss Curves
This paper introduces a new method to discover mislabeled training samples and to mitigate their impact on the training process of deep networks.
Neural Network Out-of-Distribution Detection for Regression Tasks
Neural network out-of-distribution (OOD) detection aims to identify when a model is unable to generalize to new inputs, either due to covariate shift or anomalous data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
Positional Normalization
A popular method to reduce the training time of deep neural networks is to normalize activations at each layer.
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation.
3D Object Detection From Stereo Images
Autonomous Driving
+2
Simple Black-box Adversarial Attacks
We propose an intriguingly simple method for the construction of adversarial images in the black-box setting.
BERTScore: Evaluating Text Generation with BERT
We propose BERTScore, an automatic evaluation metric for text generation.
Exact Gaussian Processes on a Million Data Points
Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data.
FastFusionNet: New State-of-the-Art for DAWNBench SQuAD
In this technical report, we introduce FastFusionNet, an efficient variant of FusionNet [12].
Simplifying Graph Convolutional Networks
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
Ranked #3 on
Text Classification
on Ohsumed
Gradient Regularized Budgeted Boosting
As machine learning transitions increasingly towards real world applications controlling the test-time cost of algorithms becomes more and more crucial.
Gradient Boosted Feature Selection
A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with the number of features and dimensions; allow the incorporation of known sparsity structure.
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
However, in this paper we argue that it is not the quality of the data but its representation that accounts for the majority of the difference.
3D Object Detection From Stereo Images
Autonomous Driving
+2
Anytime Stereo Image Depth Estimation on Mobile Devices
Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints.
Ranked #1 on
Stereo Depth Estimation
on KITTI2012
Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking
We present a data association method for vision-based multiple pedestrian tracking, using deep convolutional features to distinguish between different people based on their appearances.
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware.
Low Frequency Adversarial Perturbation
In this paper we propose to restrict the search for adversarial images to a low frequency domain.
Understanding Batch Normalization
Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks.
Resource Aware Person Re-identification across Multiple Resolutions
Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details.
Ranked #12 on
Person Re-Identification
on CUHK03 detected
Constant-Time Predictive Distributions for Gaussian Processes
One of the most compelling features of Gaussian process (GP) regression is its ability to provide well-calibrated posterior distributions.
Product Kernel Interpolation for Scalable Gaussian Processes
Recent work shows that inference for Gaussian processes can be performed efficiently using iterative methods that rely only on matrix-vector multiplications (MVMs).
CondenseNet: An Efficient DenseNet using Learned Group Convolutions
It combines dense connectivity with a novel module called learned group convolution.
On Fairness and Calibration
The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models.
Memory-Efficient Implementation of DenseNets
A 264-layer DenseNet (73M parameters), which previously would have been infeasible to train, can now be trained on a single workstation with 8 NVIDIA Tesla M40 GPUs.
On Calibration of Modern Neural Networks
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications.
Snapshot Ensembles: Train 1, get M for free
In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost.
Multi-Scale Dense Networks for Resource Efficient Image Classification
In this paper we investigate image classification with computational resource limits at test time.
Supervised Word Mover's Distance
Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning.
Densely Connected Convolutional Networks
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
Ranked #1 on
Classification
on XImageNet-12
Private Causal Inference
Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few.
Bayesian Active Model Selection with an Application to Automated Audiometry
Using this and a previously published model for healthy responses, the proposed method is shown to be capable of diagnosing the presence or absence of NIHL with drastically fewer samples than existing approaches.
Fast Distributed k-Center Clustering with Outliers on Massive Data
Clustering large data is a fundamental problem with a vast number of applications.
Deep Manifold Traversal: Changing Labels with Convolutional Features
Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership.
Compressing Convolutional Neural Networks
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision.
Compressing Neural Networks with the Hashing Trick
As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models.
Compressed Support Vector Machines
For most of the time during which we conducted this research, we were unaware of this prior work.
Differentially Private Bayesian Optimization
The success of machine learning has led practitioners in diverse real-world settings to learn classifiers for practical problems.
Image Data Compression for Covariance and Histogram Descriptors
Specifically, we show that we can reduce data sets to 16% and in some cases as little as 2% of their original size, while approximately matching the test error of kNN classification on the full training set.
A Reduction of the Elastic Net to Support Vector Machines with an Application to GPU Computing
Our second contribution is to derive a practical algorithm based on this reduction.
Parallel Support Vector Machines in Practice
In particular, we provide the first comparison of algorithms with explicit and implicit parallelization.
Non-linear Metric Learning
On various benchmark data sets, we demonstrate these methods not only match the current state-of-the-art in terms of kNN classification error, but in the case of χ2-LMNN, obtain best results in 19 out of 20 learning settings.
Cost-Sensitive Tree of Classifiers
Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e. g. search engines and email spam filters).
Co-Training for Domain Adaptation
Our algorithm is a variant of co-training, and we name it CODA (Co-training for domain adaptation).
Large Margin Multi-Task Metric Learning
Multi-task learning (MTL) improves the prediction performance on multiple, different but related, learning problems through shared parameters or representations.
Decoding Ipsilateral Finger Movements from ECoG Signals in Humans
For successful upper limb BCIs, it is important to decode finger movements from brain activity.
Large Margin Taxonomy Embedding for Document Categorization
The optimization of the semantic space incorporates large margin constraints that ensure that for each instance the correct class prototype is closer than any other.
