Search Results for author:
Found 21 papers, 11 papers with code
Bayesian Attention Modules
Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability.
Capturing Label Distribution: A Case Study in NLI
We depart from the standard practice of collecting a single reference per each training example, and find that collecting multiple references can achieve better accuracy under the fixed annotation budget.
Contextual Dropout: An Efficient Sample-Dependent Dropout Module
However, the quality of uncertainty estimation is highly dependent on the dropout probabilities.
Knowing More About Questions Can Help: Improving Calibration in Question Answering
We study calibration in question answering, estimating whether model correctly predicts answer for each question.
Bayesian Attention Belief Networks
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks.
Learning with Different Amounts of Annotation: From Zero to Many Labels
Introducing such multi label examples at the cost of annotating fewer examples brings clear gains on natural language inference task and entity typing task, even when we simply first train with a single label data and then fine tune with multi label examples.
Crossformer: Transformer with Alternated Cross-Layer Guidance
Crossformer with states sharing not only provides the desired cross-layer guidance and regularization but also reduces the memory requirement.
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.
Alignment Attention by Matching Key and Query Distributions
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains.
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
We approach text-to-image generation by combining the power of the retrained CLIP representation with an off-the-shelf image generator (GANs), optimizing in the latent space of GAN to find images that achieve maximum CLIP score with the given input text.
Ranked #48 on
Text-to-Image Generation
on MS COCO
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data.
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process.
A Unified Framework for Alternating Offline Model Training and Policy Learning
In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the environment.
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
Experiments on different tasks across open question answering, dialogue conversation, and fact verification show that our method consistently outperforms its baselines.
FlowGrad: Controlling the Output of Generative ODEs With Gradients
To further accelerate the computation of the back-propagation, we propose to use a non-uniform discretization to approximate the ODE trajectory, where we measure how straight the trajectory is and gather the straight parts into one discretization step.
A Prototype-Oriented Clustering for Domain Shift with Source Privacy
Finally, it refines the target model on the target domain data without guidance from the source model.
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied.
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years.
AutoML-GPT: Automatic Machine Learning with GPT
Ultimately, with this prompt paragraph, AutoML-GPT will automatically conduct the experiments from data processing to model architecture, hyperparameter tuning, and predicted training log.
Sliced Wasserstein with Random-Path Projecting Directions
From the RPD, we derive the random-path slicing distribution (RPSD) and two variants of sliced Wasserstein, i. e., the Random-Path Projection Sliced Wasserstein (RPSW) and the Importance Weighted Random-Path Projection Sliced Wasserstein (IWRPSW).
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
