Related papers: Learning Domain-Specific Edit Operations from Mode…
Deep learning neural network models must be large enough to adapt to their problem domain, while small enough to avoid overfitting training data during gradient descent. To balance these competing demands, over-provisioned deep learning…
Interactive artificial intelligence in the motion control field is an interesting topic, especially when universal knowledge is adaptive to multiple tasks and universal environments. Despite there being increasing efforts in the field of…
Instruction-based text editing is increasingly critical for real-world applications such as code editors (e.g., Cursor), but Large Language Models (LLMs) continue to struggle with this task. Unlike free-form generation, editing requires…
The general-purpose nature of Large Language Models (LLMs) presents a significant challenge for domain-specific applications, often leading to out-of-domain (OOD) interactions that undermine the provider's intent. Existing methods for…
Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series…
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets for measuring a model's OOD performance were designed to be…
Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes ($e.g.$, the number of convolutional layers) of a target black-box neural network can be exposed through a…
In the field of software operations, Large Language Models (LLMs) have attracted increasing attention. However, existing research has not yet achieved efficient and effective end-to-end intelligent operations due to low-quality data,…
The essence of deep learning is to exploit data to train a deep neural network (DNN) model. This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We…
Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when…
Research in machine learning has polarized into two general approaches for regression tasks: Transductive methods construct estimates directly from available data but are usually problem unspecific. Inductive methods can be much more…
The control of nonlinear dynamical systems remains a major challenge for autonomous agents. Current trends in reinforcement learning (RL) focus on complex representations of dynamics and policies, which have yielded impressive results in…
Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve strong performance, they require domain-specific training, feature engineering, and ongoing…
Editing knowledge in large language models is an attractive capability to have which allows us to correct incorrectly learnt facts during pre-training, as well as update the model with an ever-growing list of new facts. While existing model…
Dexterous multi-fingered hands can provide robots with the ability to flexibly perform a wide range of manipulation skills. However, many of the more complex behaviors are also notoriously difficult to control: Performing in-hand object…
Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…
In recent years, Large Language Models (LLMs) have emerged as a prominent area of interest across various research domains, including Process Mining (PM). Current applications in PM have predominantly centered on prompt engineering…
Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to generalize on distributions different from those from training…
Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…
This paper introduces a novel dataset construction pipeline that samples pairs of frames from videos and uses multimodal large language models (MLLMs) to generate editing instructions for training instruction-based image manipulation…