Search Results for author:
Found 40 papers, 18 papers with code
A Systematic Examination of Preference Learning through the Lens of Instruction-Following
In this work we systematically investigate how specific attributes of preference datasets affect the alignment and downstream performance of LLMs in instruction-following tasks.
Self-Generated Critiques Boost Reward Modeling for Language Models
Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF).
Law of the Weakest Link: Cross Capabilities of Large Language Models
The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
Context Diffusion: In-Context Aware Image Generation
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context.
Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression
Evaluation results show our method improves visual quality by 14%, prompt alignment by 16. 2% and scene diversity by 15. 3%, compared to prompt engineering the base Emu model for stickers generation.
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text.
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems.
PACO: Parts and Attributes of Common Objects
This motivates the need for large datasets which go beyond traditional object masks and provide richer annotations such as part masks and attributes.
Scalable Interpretability via Polynomials
We demonstrate by human subject evaluations that SPAMs are demonstrably more interpretable in practice, and are hence an effortless replacement for DNNs for creating interpretable and high-performance systems suitable for large-scale machine learning.
Neural Basis Models for Interpretability
However, these models are typically black-box deep neural networks, explained post-hoc via methods with known faithfulness limitations.
Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals
A visual counterfactual explanation replaces image regions in a query image with regions from a distractor image such that the system's decision on the transformed image changes to the distractor class.
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Model pre-training is a cornerstone of modern visual recognition systems.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(using extra training data)
Fine-Grained Image Classification
Out-of-Distribution Generalization
+3
Adaptive Methods for Aggregated Domain Generalization
In this paper, we propose a domain-adaptive approach to this problem, which operates in two steps: (a) we cluster training data within a carefully chosen feature space to create pseudo-domains, and (b) using these pseudo-domains we learn a domain-adaptive classifier that makes predictions using information about both the input and the pseudo-domain it belongs to.
Ranked #22 on
Domain Generalization
on PACS
Large-Scale Attribute-Object Compositions
We study the problem of learning how to predict attribute-object compositions from images, and its generalization to unseen compositions missing from the training data.
Adaptive Methods for Real-World Domain Generalization
We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains.
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and (b) missing object predictions.
PreDet: Large-Scale Weakly Supervised Pre-Training for Detection
State-of-the-art object detection approaches typically rely on pre-trained classification models to achieve better performance and faster convergence.
Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
Our key idea is to decorrelate feature representations of a category from its co-occurring context.
Measuring Dataset Granularity
We also investigate the interplay between dataset granularity with a variety of factors and find that fine-grained datasets are more difficult to learn from, more difficult to transfer to, more difficult to perform few-shot learning with, and more vulnerable to adversarial attacks.
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily.
Ranked #4 on
Video Quality Assessment
on MSU SR-QA Dataset
ClusterFit: Improving Generalization of Visual Representations
Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks.
Ranked #58 on
Image Classification
on iNaturalist 2018
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
To the best of our knowledge, XDC is the first self-supervised learning method that outperforms large-scale fully-supervised pretraining for action recognition on the same architecture.
Scaling and Benchmarking Self-Supervised Visual Representation Learning
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision.
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)
Large-scale weakly-supervised pre-training for video action recognition
Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?
Ranked #2 on
Egocentric Activity Recognition
on EPIC-KITCHENS-55
(Actions Top-1 (S2) metric)
Activity Driven Weakly Supervised Object Detection
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models.
Ranked #1 on
Weakly Supervised Object Detection
on Charades
Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search
Empirical evaluations of this defense strategy on ImageNet suggest that it is very effective in attack settings in which the adversary does not have access to the image database.
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
The ability to capture temporal information has been critical to the development of video understanding models.
Exploring the Limits of Weakly Supervised Pretraining
ImageNet classification is the de facto pretraining task for these models.
Ranked #228 on
Image Classification
on ImageNet
Distributed Newton Methods for Deep Neural Networks
First, to reduce the communication cost, we propose a diagonalization method such that an approximate Newton direction can be obtained without communication between machines.
Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles
We also demonstrate their usefulness in making design choices such as the number of classifiers in the ensemble and the size of a subset of data used for training that is needed to achieve a certain value of generalization error.
Gradient Boosted Decision Trees for High Dimensional Sparse Output
In this paper, we study the gradient boosted decision trees (GBDT) when the output space is high dimensional and sparse.
Batch-Expansion Training: An Efficient Optimization Framework
We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset.
Towards Geo-Distributed Machine Learning
Current solutions to learning from geo-distributed data sources revolve around the idea of first centralizing the data in one data center, and then training locally.
A Distributed Algorithm for Training Nonlinear Kernel Machines
This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce.
A distributed block coordinate descent method for training $l_1$ regularized linear classifiers
In this paper we design a distributed algorithm for $l_1$ regularization that is much better suited for such systems than existing algorithms.
An efficient distributed learning algorithm based on effective local functional approximations
In this paper we give a novel approach to the distributed training of linear classifiers (involving smooth losses and L2 regularization) that is designed to reduce the total communication costs.
