Viral News

[Submitted on 13 Mar 2024 (v1), last revised 18 Nov 2024 (this version, v2)] View a PDF of the paper titled Targeted Efficient Fine-tuning: Optimizing Parameter Updates with Data-Driven Sample Selection, by Ming Dong and 3 other authors View PDF HTML (experimental) Abstract:Fine-tuning all parameters of Large Language Models (LLMs) is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by selectively fine-tuning specific parameters. Most of the parameter efficient fine-tuning (PEFT) methods center on selecting or introducing a set of parameters to be fine-tuned. However, there are few methods that consider the impact of data samples on parameter selecting. Representative…

[Submitted on 23 Aug 2023 (v1), last revised 16 Nov 2024 (this version, v3)] View a PDF of the paper titled A Survey of Graph Unlearning, by Anwar Said and Yuying Zhao and Tyler Derr and Mudassir Shabbir and Waseem Abbas and Xenofon Koutsoukos View PDF HTML (experimental) Abstract:Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the right to be forgotten. It is evident that graph machine learning exhibits sensitivity to data privacy and adversarial attacks, necessitating the application of graph unlearning…

[Submitted on 21 May 2024 (v1), last revised 16 Nov 2024 (this version, v2)] View a PDF of the paper titled EmoEdit: Evoking Emotions through Image Manipulation, by Jingyuan Yang and 5 other authors View PDF HTML (experimental) Abstract:Affective Image Manipulation (AIM) seeks to modify user-provided images to evoke specific emotional responses. This task is inherently complex due to its twofold objective: significantly evoking the intended emotion, while preserving the original image composition. Existing AIM methods primarily adjust color and style, often failing to elicit precise and profound emotional shifts. Drawing on psychological insights, we introduce EmoEdit, which extends AIM…

[Submitted on 6 Sep 2024 (v1), last revised 17 Nov 2024 (this version, v2)] View a PDF of the paper titled You can remove GPT2's LayerNorm by fine-tuning, by Stefan Heimersheim View PDF Abstract:The LayerNorm (LN) layer in GPT-style transformer models has long been a hindrance to mechanistic interpretability. LN is a crucial component required to stabilize the training of large language models, and LN or the similar RMSNorm have been used in practically all large language models based on the transformer architecture. The non-linear nature of the LN layers is a hindrance for mechanistic interpretability as it hinders interpretation…

arXiv:2411.11748v1 Announce Type: cross Abstract: This study introduces a debiasing method for regression estimators, including high-dimensional and nonparametric regression estimators. For example, nonparametric regression methods allow for the estimation of regression functions in a data-driven manner with minimal assumptions; however, these methods typically fail to achieve $sqrt{n}$-consistency in their convergence rates, and many, including those in machine learning, lack guarantees that their estimators asymptotically follow a normal distribution. To address these challenges, we propose a debiasing technique for nonparametric estimators by adding a bias-correction term to the original estimators, extending the conventional one-step estimator used in semiparametric analysis. Specifically, for…

[Submitted on 28 Feb 2024 (v1), last revised 18 Nov 2024 (this version, v3)] View a PDF of the paper titled SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model, by Bin Cao and 6 other authors View PDF HTML (experimental) Abstract:In the rapidly evolving area of image synthesis, a serious challenge is the presence of complex artifacts that compromise perceptual realism of synthetic images. To alleviate artifacts and improve quality of synthetic images, we fine-tune Vision-Language Model (VLM) as artifact classifier to automatically identify and classify a wide range of artifacts and provide supervision for further optimizing…

[Submitted on 29 Jun 2024 (v1), last revised 18 Nov 2024 (this version, v3)] View a PDF of the paper titled ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees, by Zhiyuan Wang and 8 other authors View PDF HTML (experimental) Abstract:Uncertainty quantification (UQ) in natural language generation (NLG) tasks remains an open challenge, exacerbated by the closed-source nature of the latest large language models (LLMs). This study investigates applying conformal prediction (CP), which can transform any heuristic uncertainty notion into rigorous prediction sets, to black-box LLMs in open-ended NLG tasks. We introduce a novel uncertainty measure based…

When it comes to managing an insurance business, the tools you choose make all the difference. Insurance agents today are flooded with choices for software solutions. But with so many options, how do you pick the right one? Two of the most popular types are customer relationship management (CRM) systems and agency management systems (AMS). Both promise to streamline your workflow, boost productivity, and help you stay organized. Yet they each have distinct purposes, features, and benefits.   Let’s dive into the key differences and see which type of software could be the perfect fit for your insurance business.    What…

Providence Health's extensive network spans 50+ hospitals and numerous other facilities across multiple states, presenting many challenges in predicting patient volume and daily census within specific departments. This information is critical to making informed decisions about short-term and long-term staffing needs, transfer of patients, and general operational awareness.  In the early stages of Databricks adoption, Providence sought to create a simple baseline census model that would get new requests going quickly, aid in exploration and in many cases provide an initial forecast.  We also realized that scaling this census to support thousands of departments in near real-time was going to…

[Submitted on 30 Apr 2024 (v1), last revised 17 Nov 2024 (this version, v2)] View a PDF of the paper titled Improved AutoEncoder with LSTM module and KL divergence, by Wei Huang and 3 other authors View PDF HTML (experimental) Abstract:The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep convolutional autoencoder (CAE) network and deep supporting vector data description (SVDD) model have been universally employed and have demonstrated significant success in detecting anomalies. However, the over-reconstruction ability of CAE network for anomalous data can easily lead to high false…