Search Results for author:
Found 19 papers, 10 papers with code
Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
In this work, we introduce VistaLLM, a powerful visual system that addresses coarse- and fine-grained VL tasks over single and multiple input images using a unified framework.
Llama 2: Open Foundation and Fine-Tuned Chat Models
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.
Ranked #2 on
Question Answering
on PubChemQA
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes
Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward passes.
Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization
In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning.
Progressive Prompts: Continual Learning for Language Models
We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models.
Uniform Masking Prevails in Vision-Language Pretraining
Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining.
Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI
Evaluating an explanation's faithfulness is desired for many reasons such as trust, interpretability and diagnosing the sources of model's errors.
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited.
Unsupervised Learning of Dense Visual Representations
VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks.
The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages.
Adversarial Computation of Optimal Transport Maps
We show that during training, our generator follows the $W_2$-geodesic between the initial and the target distributions.
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Generative adversarial networks have been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks.
W2GAN: RECOVERING AN OPTIMAL TRANSPORT MAP WITH A GAN
In this work we address the converse question: is it possible to recover an optimal map in a GAN fashion?
Learning Distributed Representations from Reviews for Collaborative Filtering
However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model's ability to act as a regularizer of the product representations.
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data.
Calibrating Energy-based Generative Adversarial Networks
In this paper, we propose to equip Generative Adversarial Networks with the ability to produce direct energy estimates for samples. Specifically, we propose a flexible adversarial training framework, and prove this framework not only ensures the generator converges to the true data distribution, but also enables the discriminator to retain the density information at the global optimal.
Ranked #17 on
Conditional Image Generation
on CIFAR-10
(Inception score metric)
First Result on Arabic Neural Machine Translation
Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Dynamic Capacity Networks
The low-capacity sub-networks are applied across most of the input, but also provide a guide to select a few portions of the input on which to apply the high-capacity sub-networks.
