Recent & Upcoming Talks

This presentation covers an overview of perturbation-based approaches, as well as evaluation methods of explanations.

Across the tasks of summarization, helpful dialogue generation, and harmless dialogue generation, this papers show that RLAIF achieves comparable performance to RLHF.

This paper introduces DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL.

This paper begins with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, it presents a thorough overview of hallucination detection methods and benchmarks

The paper shows that LLMs are decent zero-shot reasoners by simply adding “Let’s think step by step” before each answer. Experimental results demonstrate that the Zero-shot-CoT, using the same single prompt template, significantly outperforms zero-shot LLM performances on diverse benchmark reasoning tasks

A reinforcement learning approach to solve the vehicle routing problem.

In this paper, the authors introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values.

In this work, the authors revisit the most fundamental building block in deep learning, the multi-layer perceptron (MLP), and study the limits of its performance on vision tasks.

In this paper, the authors present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently.

This paper proposes two binary imbalanced data classification methods with extreme learning machine autoencoders and generative models. Their methods outperform SMOTE and similar data balancing tools on most benchmark datasets.

This paper discusses the available methods to detect change points in time-series data.

A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds for data in-the-wild, where instances belonging to novel classes may appear at testing time. Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data.

In this position paper, the authors define interpretability and describe when interpretability is needed (and when it is not). Next, they suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.

This paper reduces drug-drug interaction in automated medication recommendation with help of self-supervised adversarial distribution regularization

This research aimed to develop a lifestyle intervention system with an emphasis on time series forecasting and also to develop a generic multimodal activity forecasting scheme that can be used with either early fusion or late fusion mechanisms.

This paper provides an overview of basic and advanced approaches of time-series data augmentation.

This paper proposes GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting.

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision.

A reinforcement learning approach to solve the vehicle routing problem.

This paper addresses the generalization gap on large neural networks with adaptive gradient-based optimizers and proposes a partially adaptive solution to overcome the problem.

We focus on devising algorithms that combine data about physical activity and engagement with the app to predict future physical activity performance.