Editing Tasks Research Articles

Amphiphilic Oligonucleotide Derivatives—Promising Tools for Therapeutics

Recent advances in genetics and nucleic acid chemistry have created fundamentally new tools, both for practical applications in therapy and diagnostics and for fundamental genome editing tasks. Nucleic acid-based therapeutic agents offer a distinct advantage of selectively targeting the underlying cause of the disease. Nevertheless, despite the success achieved thus far, there remain unresolved issues regarding the improvement of the pharmacokinetic properties of therapeutic nucleic acids while preserving their biological activity. In order to address these challenges, there is a growing focus on the study of safe and effective delivery methods utilising modified nucleic acid analogues and their lipid bioconjugates. The present review article provides an overview of the current state of the art in the use of chemically modified nucleic acid derivatives for therapeutic applications, with a particular focus on oligonucleotides conjugated to lipid moieties. A systematic analysis has been conducted to investigate the ability of amphiphilic oligonucleotides to self-assemble into micelle-like structures, as well as the influence of non-covalent interactions of such derivatives with serum albumin on their biodistribution and therapeutic effects.

An improved face attributes editing method based on DDIM

The main advantage of DDIM is that it guarantees the quality of the generated images while increasing the efficiency of the generation by modifying the sampling strategy in the diffusion process. DiffusionRig, which addresses the problem of maintaining identity consistency by learning the person-specific facial prior in a tiny personalized dataset, is a successful representation of the DDIM strategy. Based on DiffusionRig, in this article, we propose an improved face attributes editing method based on DDIM to improve naturalness and accuracy of editing results in complex face attribute editing tasks and the generalization ability. Our method combines DDIM and DECA together and use two-stage training strategy. To reduce DiffusionRig’s limitations in handling face attribute editing tasks that require nonlinear understanding and fine-tuning, our method also introduces a channel attention mechanism and a depth-separable convolution technique in the training model. In the first stage we trained our model on the open FFHQ dataset, which consists of 30,000 high-resolution face image. In the second stage, the model was refined by using a tiny personalized dataset. Face attribute editing experiments,comparative experiment with DiffusionRig, and a series of ablation experiments have been performed. Then, the validity of our improved method is verified by qualitative and quantitative analysis.

PFB-Diff: Progressive Feature Blending diffusion for text-driven image editing

Diffusion models have demonstrated their ability to generate diverse and high-quality images, sparking considerable interest in their potential for real image editing applications. However, existing diffusion-based approaches for local image editing often suffer from undesired artifacts due to the latent-level blending of the noised target images and diffusion latent variables, which lack the necessary semantics for maintaining image consistency. To address these issues, we propose PFB-Diff, a Progressive Feature Blending method for Diffusion-based image editing. Unlike previous methods, PFB-Diff seamlessly integrates text-guided generated content into the target image through multi-level feature blending. The rich semantics encoded in deep features and the progressive blending scheme from high to low levels ensure semantic coherence and high quality in edited images. Additionally, we introduce an attention masking mechanism in the cross-attention layers to confine the impact of specific words to desired regions, further improving the performance of background editing and multi-object replacement. PFB-Diff can effectively address various editing tasks, including object/background replacement and object attribute editing. Our method demonstrates its superior performance in terms of editing accuracy and image quality without the need for fine-tuning or training. Our implementation is available at https://github.com/CMACH508/PFB-Diff.

A Survey on Video Diffusion Models

The recent wave of AI-generated content (AIGC) has witnessed substantial success in computer vision, with the diffusion model playing a crucial role in this achievement. Due to their impressive generative capabilities, diffusion models are gradually superseding methods based on GANs and auto-regressive Transformers, demonstrating exceptional performance not only in image generation and editing, but also in the realm of video-related research. However, existing surveys mainly focus on diffusion models in the context of image generation, with few up-to-date reviews on their application in the video domain. To address this gap, this paper presents a comprehensive review of video diffusion models in the AIGC era. Specifically, we begin with a concise introduction to the fundamentals and evolution of diffusion models. Subsequently, we present an overview of research on diffusion models in the video domain, categorizing the work into three key areas: video generation, video editing, and other video understanding tasks. We conduct a thorough review of the literature in these three key areas, including further categorization and practical contributions in the field. Finally, we discuss the challenges faced by research in this domain and outline potential future developmental trends. A comprehensive list of video diffusion models studied in this survey is available at https://github.com/ChenHsing/Awesome-Video-Diffusion-Models.

Retrosynthesis prediction with an iterative string editing model

Retrosynthesis is a crucial task in drug discovery and organic synthesis, where artificial intelligence (AI) is increasingly employed to expedite the process. However, existing approaches employ token-by-token decoding methods to translate target molecule strings into corresponding precursors, exhibiting unsatisfactory performance and limited diversity. As chemical reactions typically induce local molecular changes, reactants and products often overlap significantly. Inspired by this fact, we propose reframing single-step retrosynthesis prediction as a molecular string editing task, iteratively refining target molecule strings to generate precursor compounds. Our proposed approach involves a fragment-based generative editing model that uses explicit sequence editing operations. Additionally, we design an inference module with reposition sampling and sequence augmentation to enhance both prediction accuracy and diversity. Extensive experiments demonstrate that our model generates high-quality and diverse results, achieving superior performance with a promising top-1 accuracy of 60.8% on the standard benchmark dataset USPTO-50 K.

Computational Illusion Knitting

Illusion-knit fabrics reveal distinct patterns or images depending on the viewing angle. Artists have manually achieved this effect by exploiting "microgeometry," i.e., small differences in stitch heights. However, past work in computational 3D knitting does not model or exploit designs based on stitch height variation. This paper establishes a foundation for exploring illusion knitting in the context of computational design and fabrication. We observe that the design space is highly constrained, elucidate these constraints, and derive strategies for developing effective, machine-knittable illusion patterns. We partially automate these strategies in a new interactive design tool that reduces difficult patterning tasks to familiar image editing tasks. Illusion patterns also uncover new fabrication challenges regarding mixed colorwork and texture; we describe new algorithms for mitigating fabrication failures and ensuring high-quality knit results.

Artificial Intelligence (AI) is Not A Writing Gods, So Why Do Post-Graduate Students Believe It?

This study was aimed at understanding graduate students' preferences in applying AI when dealing with their class papers and projects in Indonesia. It also sought to understand how students who have used AI in previous writing feel about such experience. This study adopted a phenomenological research method in order to elicit in-depth insights into the concerns of the students. The participants included graduate students from four universities in Indonesia. These data were gathered using semi-structured interviews of 30 students who had experience using AI for their academic writing. Guided by understanding the decision-making process, perceived benefits, and drawbacks of AI, and overall experiences, interview questions were prepared. One-way thematic analysis was conducted with the interview data. Students seemed to view AI applications as only helping with formatting and editing tasks, as most of them would like to have the opportunity to do the major work by themselves for better learning. Another underlying strong theme emerging here is related to AI overdependency and unequal access to it. The results offer insights into the respective areas that can be used by educators and institutions to provide a balance between the rising AI in use and support for independent learning within academics.

Editar os Pensamentos de Pascal: considerações históricas e análise da edição de Alain Cantillon

The posthumous discovery of Blaise Pascal’s writings on Christianity posed a challenge for his family and friends: how should these writings be edited? The present work makes a brief inquiry into this challenge and offers an overview of the main editions of Pascal’s Pensées since the Seventeenth century, including that of Allain Cantillon, published in 2023. The purpose of the present work, therefore, encompasses the following steps: (I) some historical remarks concerning the task of editing Pensées, (II) an overview of its main editions, and finally (III and IV) a description and analysis of Cantillon’s editorial proposal.

EQUILIBRIUM IN TECHNICAL WRITING: HARMONIZING OBJECTIVITY WITH ADVOCACY

The task of editing is strenuous, and the most challenging one is to reach the target goals within the time limitation. Equilibrium is the stage of finding a balance between two opposite things. In this research piece, the standpoint of an editor will be analyzed from the perspective of objectivity and advocacy. The fact cannot be denied that editors (many of them) spend an extensive time only to rectify the issues related to lexicon. However, painfully true, many of them overlook the rhythm of balancing act, and only for that lethargic activity, they face a challenging situation to reach the laudable phase. The goal of this research task is to help the future editors and the technical writers to connect the eclectic issues related to the balancing act.

Systematic review on Artificial Intelligence in the editorial management of scientific journals

INTRODUCTION: scientific journals play a crucial role in the dissemination and validation of scientific knowledge, and editorial management ranges from conceptualization to post-publication of content. Artificial intelligence (AI) has had a great impact on scientific communication and editorial management of scientific journals. AI can offer solutions and benefits for editorial management, but it also poses technical, economic, social and ethical challenges that should be considered and approached with caution and responsibility. OBJECTIVE: to describe the benefits and limitations of the use of AI in the editorial management of scientific journals through a systematic literature review. METHOD: a systematic literature review was conducted based on the PRISMA methodology. An information search was carried out in different bibliographic database systems, indexing systems and search engines, and inclusion and exclusion criteria were applied to the identified studies. RESULTS: the information search allowed retrieving a total of 2750 sources, of which 10 articles that met the stated criteria were included. Benefits such as the facilitation of writing, translation, review and editing tasks were identified, as well as limitations related to ethical issues, bias, errors and plagiarism generated by AI. CONCLUSIONS: While AI can streamline the production and analysis of information distribution, it also poses challenges in terms of reliability, ethics and authenticity of published content. It requires the critical involvement of human intelligence for proper exploitation.

Weather Translation via Weather-Cue Transferring.

In this article, the weather translation task is proposed, which aims to transfer the weather type of the image from one category to another. Weather translation is a complicated image weather editing task that changes the weather cue of an image across multiple weather types, and it is related to image restoration, image editing, and photographic style transfer tasks. Although lots of approaches have been developed for traditional image translation and restoration tasks, only few of them are capable of handling the multicategory weather types problem with a single network due to the rich categories and highly complicated semantic structures of weather images. Especially, it is difficult to change the weather cue while preserving the weather-invariant area. To solve these issues, we developed a weather-cue guided multidomain translation approach based on StarGAN v2, termed WeatherGAN. In the proposed model, the core generator is redesigned to transfer the weather cue according to the target weather type. The weather segmentation module is first introduced to acquire the weather semantic structure of images in a weakly supervised multitask manner. In addition, a weather clues module is presented to reprocess the weather segmentation into a weather-specific clues map, which identifies the weather-invariant and weather-cue areas clearly. Extensive studies and evaluations show that our approach outperforms the state of the art. The data and source code will be publicly available soon after the manuscript is accepted.

SwivelTouch: Boosting Touchscreen Input with 3D Finger Rotation Gesture

Today, touchscreens stand as the most prevalent input devices of mobile computing devices (smartphones, tablets, smartwatches). Yet, compared with desktop or laptop computers, the limited shortcut keys and physical buttons on touchscreen devices, coupled with the fat finger problem, often lead to slower and more error-prone input and navigation, especially when dealing with text editing and other complex interaction tasks. We introduce an innovative gesture set based on finger rotations in the yaw, pitch, and roll directions on a touchscreen, diverging significantly from traditional two-dimensional interactions and promising to expand the gesture library. Despite active research in estimation of finger angles, however, the previous work faces substantial challenges, including significant estimation errors and unstable sequential outputs. Variability in user behavior further complicates the isolation of movements to a single rotational axis, leading to accidental disturbances and screen coordinate shifts that interfere with the existing sliding gestures. Consequently, the direct application of finger angle estimation algorithms for recognizing three-dimensional rotational gestures is impractical. SwivelTouch leverages the analysis of finger movement characteristics on the touchscreen captured through original capacitive image sequences, which aims to rapidly and accurately identify these advanced 3D gestures, clearly differentiating them from conventional touch interactions like tapping and sliding, thus enhancing user interaction with touch devices and meanwhile compatible with existing 2D gestures. User study further confirms that the implementation of SwivelTouch significantly enhances the efficiency of text editing on smartphones.

Spatial-Contextual Discrepancy Information Compensation for GAN Inversion

Most existing GAN inversion methods either achieve accurate reconstruction but lack editability or offer strong editability at the cost of fidelity. Hence, how to balance the distortion-editability trade-off is a significant challenge for GAN inversion. To address this challenge, we introduce a novel spatial-contextual discrepancy information compensation-based GAN-inversion method (SDIC), which consists of a discrepancy information prediction network (DIPN) and a discrepancy information compensation network (DICN). SDIC follows a ``compensate-and-edit'' paradigm and successfully bridges the gap in image details between the original image and the reconstructed/edited image. On the one hand, DIPN encodes the multi-level spatial-contextual information of the original and initial reconstructed images and then predicts a spatial-contextual guided discrepancy map with two hourglass modules. In this way, a reliable discrepancy map that models the contextual relationship and captures fine-grained image details is learned. On the other hand, DICN incorporates the predicted discrepancy information into both the latent code and the GAN generator with different transformations, generating high-quality reconstructed/edited images. This effectively compensates for the loss of image details during GAN inversion. Both quantitative and qualitative experiments demonstrate that our proposed method achieves the excellent distortion-editability trade-off at a fast inference speed for both image inversion and editing tasks. Our code is available at https://github.com/ZzqLKED/SDIC.

History Matters: Temporal Knowledge Editing in Large Language Model

The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due to external shifts in the real world which should be updated. Prevailing efforts in model editing conflate these two distinct categories of edits arising from distinct reasons and directly modify the original knowledge in models into new knowledge. However, we argue that preserving the model's original knowledge remains pertinent. Specifically, if a model's knowledge becomes outdated due to evolving worldly dynamics, it should retain recollection of the historical knowledge while integrating the newfound knowledge. In this work, we introduce the task of Temporal Knowledge Editing (TKE) and establish a benchmark AToKe (Assessment of TempOral Knowledge Editing) to evaluate current model editing methods. We find that while existing model editing methods are effective at making models remember new knowledge, the edited model catastrophically forgets historical knowledge. To address this gap, we propose a simple and general framework termed Multi-Editing with Time Objective (METO) for enhancing existing editing models, which edits both historical and new knowledge concurrently and optimizes the model's prediction for the time of each fact. Our assessments demonstrate that while AToKe is still difficult, METO maintains the effectiveness of learning new knowledge and meanwhile substantially improves the performance of edited models on utilizing historical knowledge.

Preparing Future Technical Editors for an Artificial Intelligence-enabled Workplace

How should instructors adapt technical editing courses to account for generative artificial intelligence (AI)? This article addresses what generative AI means for technical editing pedagogy. While AI tools may be able to address rote editing tasks, expert editors are still needed to provide accessible, ethical, and justice-oriented edits. After reviewing impacts of generative AI on editing praxis, the author focuses on the microcredentials that she built into an editing course in order to address these impacts pedagogically. The goal was to enable students to understand AI, argue for their expertise, and edit from ethical and social justice perspectives.

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

Large language models (LLMs) have shown great success in various Natural Language Processing (NLP) tasks, whist they still need updates after deployment to fix errors or keep pace with the changing knowledge in the world. Researchers formulate such problem as Model Editing and have developed various editors focusing on different axes of editing properties. However, current editors can hardly support all properties and rely on heavy computational resources. In this paper, we propose a plug-in Model Editing method based on neuron-indexed dynamic LoRA (MELO), which alters the behavior of language models by dynamically activating certain LoRA blocks according to the index built in an inner vector database. Our method satisfies various editing properties with high efficiency and can be easily integrated into multiple LLM backbones. Experimental results show that our proposed MELO achieves state-of-the-art editing performance on three sequential editing tasks (document classification, question answering and hallucination correction), while requires the least trainable parameters and computational cost.

Speech driven video editing via an audio-conditioned diffusion model

Taking inspiration from recent developments in visual generative tasks using diffusion models, we propose a method for end-to-end speech-driven video editing using a denoising diffusion model. Given a video of a talking person, and a separate auditory speech recording, the lip and jaw motions are re-synchronised without relying on intermediate structural representations such as facial landmarks or a 3D face model. We show this is possible by conditioning a denoising diffusion model on audio mel spectral features to generate synchronised facial motion. Proof of concept results are demonstrated on both single-speaker and multi-speaker video editing, providing a baseline model on the CREMA-D audiovisual data set. To the best of our knowledge, this is the first work to demonstrate and validate the feasibility of applying end-to-end denoising diffusion models to the task of audio-driven video editing. All code, datasets, and models used as part of this work are made publicly available here: https://danbigioi.github.io/DiffusionVideoEditing/.

Edit propagation via color palettes

The ability to ease operation and real-time feedback to image editing has attracted increasing attention in our everyday lives. Existing edit propagation approaches typically formulate the color editing task as a quadratic energy optimization problem, which is computationally expensive and requires a lot of user interactions. To address this problem, in this paper, we propose a novel edit propagation method based on color palette. We first extract a color palette from the input image, and then calculate the mixing weights of the image pixels with respect to the extracted palette. Finally, we solve for an edited palette according to user edits, to propagate local edits to the whole image. Our main contributions include formulating the edit propagation as a palette-based optimization problem that can be solved efficiently, and requiring only fewer user interactions than existing methods. We have demonstrated our method for color editing on a wide range of examples. Compared to existing methods, our approach is more efficient and friendly for novice users due to its ease of interaction.

SDMuse: Stochastic Differential Music Editing and Generation via Hybrid Representation

While deep generative models have empowered music generation, it remains a challenging and under-explored problem to edit an existing musical piece at fine granularity. In this paper, we propose SDMuse, a unified Stochastic Differential Music editing and generation framework, which can not only compose a whole musical piece from scratch, but also modify existing musical pieces in many ways, such as combination, continuation, inpainting, and style transferring. The proposed SDMuse follows a two-stage pipeline to achieve music generation and editing on top of a hybrid representation including pianoroll and MIDI-event. In particular, SDMuse first generates/edits pianoroll by iteratively denoising through a stochastic differential equation (SDE) based on a diffusion model generative prior, and then refines the generated pianoroll and predicts MIDI-event tokens auto-regressively. We evaluate the generated music of our method on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ailabs1k7</i> pop music dataset in terms of quality and controllability on various music editing and generation tasks. Experimental results demonstrate the effectiveness of our proposed stochastic differential music editing and generation process, as well as the hybrid representations.

Bilinear Models of Parts and Appearances in Generative Adversarial Networks.

Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces of pre-trained GANs. However, existing methods are often tailored to specific GAN architectures and are limited to either discovering global semantic directions that do not facilitate localized control, or require some form of supervision through manually provided regions or segmentation masks. In this light, we present an architecture-agnostic approach that jointly discovers factors representing spatial parts and their appearances in an entirely unsupervised fashion. These factors are obtained by applying a semi-nonnegative tensor factorization on the feature maps, which in turn enables context-aware local image editing with pixel-level control. In addition, we show that the discovered appearance factors correspond to saliency maps that localize concepts of interest, without using any labels. Experiments on a wide range of GAN architectures and datasets show that, in comparison to the state of the art, our method is far more efficient in terms of training time and, most importantly, provides much more accurate localized control.