Tootfinder

Towards Scalable and Consistent 3D Editing
Ruihao Xia, Yang Tang, Pan Zhou
https://arxiv.org/abs/2510.02994 https://arxiv.org/pdf/2510.02994

Towards Scalable and Consistent 3D Editing
3D editing - the task of locally modifying the geometry or appearance of a 3D asset - has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need for cross-view consistency, structural fidelity, and fine-grained controllability. Existing approaches are often slow, prone to geometric distortions, or dependent on manual and accurate 3D masks that are error-prone and impractical. To address these challeng…

C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing
Zeng Tao, Zheng Ding, Zeyuan Chen, Xiang Zhang, Leizhi Li, Zhuowen Tu
https://arxiv.org/abs/2510.04539 ht…

C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing
Existing 2D-lifting-based 3D editing methods often encounter challenges related to inconsistency, stemming from the lack of view-consistent 2D editing models and the difficulty of ensuring consistent editing across multiple views. To address these issues, we propose C3Editor, a controllable and consistent 2D-lifting-based 3D editing framework. Given an original 3D representation and a text-based editing prompt, our method selectively establishes a view-consistent 2D editing model to achieve sup…

JSON Whisperer: Efficient JSON Editing with LLMs
Sarel Duanis, Asnat Greenstein-Messica, Eliya Habba
https://arxiv.org/abs/2510.04717 https://arxiv.org/pdf…

JSON Whisperer: Efficient JSON Editing with LLMs
Large language models (LLMs) can modify JSON documents through natural language commands, but current approaches regenerate entire structures for each edit, resulting in computational inefficiency. We present JSON Whisperer, a framework that enables LLMs to generate RFC 6902 diff patches-expressing only the necessary modifications-rather than complete documents. We identify two key challenges in patch-based editing: (1) LLMs often miss related updates when generating isolated patches, and (2) a…

Recomposer: Event-roll-guided generative audio editing
Daniel P. W. Ellis, Eduardo Fonseca, Ron J. Weiss, Kevin Wilson, Scott Wisdom, Hakan Erdogan, John R. Hershey, Aren Jansen, R. Channing Moore, Manoj Plakal
https://arxiv.org/abs/2509.05256

Recomposer: Event-roll-guided generative audio editing
Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understanding of the data domain. We present a system for editing individual sound events within complex scenes able to delete, insert, and enhance individual sound events based on textual edit descriptions (e.g., ``enhance Door'') and a graphical representation of the event timing derived from an ``event ro…

MIT Scientists Unlock a New Level of Precision in Gene Editing
https://scitechdaily.com/mit-scientists-unlock-a-new-level-of-precision-in-gene-editing/

CBS Abruptly Changes Rules for Editing 'Face the Nation' Interviews (Michael M. Grynbaum/New York Times)
https://www.nytimes.com/2025/09/05/business/cbs-face-the-nation-editing-rules.html?unlocked_article_code=1.jk8.-ehM.s2ZUPkOOll5E&smid=url-share
http://www.memeorandum.com/250905/p91#a250905p91

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
Uro\v{s} \v{S}majdek, Ciril Bohak
https://arxiv.org/abs/2510.04971 https://

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
We present an interactive visualization system for exploring named entities and their relationships across document collections. The system is designed around a graph-based representation that integrates three types of nodes: documents, entity mentions, and entities. Connections capture two key relationship types: (i) identical entities across contexts, and (ii) co-locations of mentions within documents. Multiple coordinated views enable users to examine entity occurrences, discover clusters of…

Today's job: editing a former student's brilliant paper on a topic near and dear to my heart for publication in the journal. #Academia has its days.

Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Le Zhuo, Songhao Han, Yuandong Pu, Boxiang Qiu, Sayak Paul, Yue Liao, Yihao Liu, Jie Shao, Xi Chen, Si Liu, Hongsheng Li
https://arxiv.org/abs/2510.05091

Factuality Matters: When Image Generation and Editing Meet Structured Visuals
While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning, text rendering, and multimodal reasoning for factual fidelity. To address this, we present the first comprehensive, systematic investigation of this domain, encompassing data construction, model training, and an evaluation benchmark. First, we construct a large…

EditLens: Quantifying the Extent of AI Editing in Text
Katherine Thai, Bradley Emi, Elyas Masrour, Mohit Iyyer
https://arxiv.org/abs/2510.03154 https://arx…

EditLens: Quantifying the Extent of AI Editing in Text
A significant proportion of queries to large language models ask them to edit user-provided text, rather than generate new text from scratch. While previous work focuses on detecting fully AI-generated text, we demonstrate that AI-edited text is distinguishable from human-written and AI-generated text. First, we propose using lightweight similarity metrics to quantify the magnitude of AI editing present in a text given the original human-written text and validate these metrics with human annota…

SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting
Sung-Yeon Park, Adam Lee, Juanwu Lu, Can Cui, Luyang Jiang, Rohit Gupta, Kyungtae Han, Ahmadreza Moradipari, Ziran Wang
https://arxiv.org/abs/2510.02469

SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting
Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing capabilities. To address these challenges, we present SIMSplat, a predictive driving scene editor with language-aligned Gaussian splatting. As a language-controlled editor, SIMSplat enables intuitive manipulation using natural language prompts. By aligning language wi…

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
Ronen Kamenetsky, Sara Dorfman, Daniel Garibi, Roni Paiss, Or Patashnik, Daniel Cohen-Or
https://arxiv.org/abs/2510.05081

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where changing one attribute does not unintentionally alter others, and continuous control, where the strength of an edit can be smoothly adjusted. We introduce a method for disentangled and continuous editing through token-level manipulation of text embeddings. The ed…

I'm doing a Wikiversity edit right now over at
en.wikiversity.org/wiki/Editing_Internet_Texts/Persuasive_Language_in_Advertising
just a small spelling mistake...
Will post my edit into this post once it is published!
Edit summary(still not publilshed):
small spelling edit: "of our lives" instead of "of out lives"
This is a minor edit ==> CHECK BOX ✅

Editing Internet Texts/Persuasive Language in Advertising - Wikiversity

Rare view of my desk during video editing.
With appropriate beverage vessels.

VideoGuard: Protecting Video Content from Unauthorized Editing
Junjie Cao, Kaizhou Li, Xinchun Yu, Hongxiang Li, Xiaoping Zhang
https://arxiv.org/abs/2508.03480 https://

VideoGuard: Protecting Video Content from Unauthorized Editing
With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these capabilities for misleading activities. Although existing research has attempted to shield photographic images from being manipulated by generative models, there remains a significant disparity in the protection offered to video content editing. To bridge the gap, we pr…

A productive day so far!
✅ Client video recording & editing
✅ Client workshop on conversations and relationships at work
✅ Public webinar on coaching
Next up: recording a podcast with a great friend, all about the need for intentional #SelfCare. 🎧 ♥️
#PsychologistAtWork

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[17/17]:
- SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
Ronen Kamenetsky, Sara Dorfman, Daniel Garibi, Roni Paiss, Or Patashnik, Daniel Cohen-Or

FPEdit: Robust LLM Fingerprinting through Localized Knowledge Editing
Shida Wang, Chaohu Liu, Yubo Wang, Linli Xu
https://arxiv.org/abs/2508.02092 https://…

FPEdit: Robust LLM Fingerprinting through Localized Knowledge Editing
Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets. Nevertheless, these AI assets remain vulnerable to unauthorized redistribution and commercial exploitation through fine-tuning or black-box deployment. Current fingerprinting approaches face a fundamental trade-off: intrinsic methods require full parameter access, while backdoor-based techniques employ statistically anomalous triggers…

I keep using “lol” too often in work messages. Finding myself editing it out to replace with the more professional “haha”

Upgraded image editing in Gemini is jaw dropping ,
#ai

Image editing in Gemini just got a major upgrade
Transform images in amazing new ways with updated native image editing in the Gemini app.

DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing
Qi Li, Shuwen Qiu, Julien Han, Xingzi Xu, Mehmet Saygin Seyfioglu, Kee Kiat Koo, Karim Bouyarmane
https://arxiv.org/abs/2510.04797

DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing
The rapid growth of e-commerce has intensified the demand for Virtual Try-On (VTO) technologies, enabling customers to realistically visualize products overlaid on their own images. Despite recent advances, existing VTO models face challenges with fine-grained detail preservation, robustness to real-world imagery, efficient sampling, image editing capabilities, and generalization across diverse product categories. In this paper, we present DiT-VTON, a novel VTO framework that leverages a Diffus…

Eigenvoice Synthesis based on Model Editing for Speaker Generation
Masato Murata, Koichi Miyazaki, Tomoki Koriyama, Tomoki Toda
https://arxiv.org/abs/2507.03377

Eigenvoice Synthesis based on Model Editing for Speaker Generation
Speaker generation task aims to create unseen speaker voice without reference speech. The key to the task is defining a speaker space that represents diverse speakers to determine the generated speaker trait. However, the effective way to define this speaker space remains unclear. Eigenvoice synthesis is one of the promising approaches in the traditional parametric synthesis framework, such as HMM-based methods, which define a low-dimensional speaker space using pre-stored speaker features. Thi…

Bin grade auf der Arbeit, die info wird noch näher bearbeitet
vorstellungDreirad.md - Storage Share
https://mycloud.gridcafe.de/s/MkbjJgsGA2DHzb6?dir=/&editing=false&openfile=true

Dreirad
Storage Share - powered by Nextcloud

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
Chenglei Shen, Zhongxiang Sun, Teng Shi, Xiao Zhang, Jun Xu
https://arxiv.org/abs/2508.04530

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness. Existing representation editing methods, by naively injecting style signals, overlook this collateral impact and frequently contaminate the model's core truthfulness representations, resulting in reduced answer correctness. We term this phenomenon stylization-…

Adobe launches its Premiere video editing software on iPhone for the first time; general editing is free, but Adobe charges for credits to generate AI content (Chris Welch/Bloomberg)
https://www.bloomberg.com/news/articles/2025-…

Object-AVEdit: An Object-level Audio-Visual Editing Model
Youquan Fu, Ruiyang Si, Hongfa Wang, Dongzhan Zhou, Jiacheng Sun, Ping Luo, Di Hu, Hongyuan Zhang, Xuelong Li
https://arxiv.org/abs/2510.00050 …

Object-AVEdit: An Object-level Audio-Visual Editing Model
There is a high demand for audio-visual editing in video post-production and the film making field. While numerous models have explored audio and video editing, they struggle with object-level audio-visual operations. Specifically, object-level audio-visual editing requires the ability to perform object addition, replacement, and removal across both audio and visual modalities, while preserving the structural information of the source instances during the editing process. In this paper, we pres…

Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada
https://arxiv.org/abs/2509.05285 h…

Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
Recent advances in text-driven 3D scene editing and stylization, which leverage the powerful capabilities of 2D generative models, have demonstrated promising outcomes. However, challenges remain in ensuring high-quality stylization and view consistency simultaneously. Moreover, applying style consistently to different regions or objects in the scene with semantic correspondence is a challenging task. To address these limitations, we introduce techniques that enhance the quality of 3D stylizati…

How The Minnesota Star Tribune bolstered its shoe-leather reporting by using ChatGPT to analyze handwritten Faux Cyrillic journal entries of a mass shooter (Tom Scheck/Poynter)
https://www.poynter.org/reporting-editing/2025/minnesota-star-tribun…

How the Minnesota Star Tribune used AI to bolster its shoe-leather reporting to background a mass shooter - Poynter
A team of journalists relentlessly tracked the shooter’s digital and paper trail. But AI provided deeper insight into her thoughts before the shooting.

I somehow stumbled upon the most arthouse film I can think of:
☑️filmed on analog film stock
☑️very slow pacing but still has jarring editing decisions
☑️scenes with inharmonious violin music
☑️scenes without any sound at all
☑️topless woman
☑️bondage scenes
☑️dream-like scenes
☑️woman growing an actual horse tail 😳
htt…

Generating High-Quality Datasets for Code Editing via Open-Source Language Models
Zekai Zhang, Mingwei Liu, Zhenxi Chen, Linxi Liang, Yuxuan Chen, Guangsheng Ou, Yanlin Wang, Dan Li, Xin Peng, Zibin Zheng
https://arxiv.org/abs/2509.25203

Generating High-Quality Datasets for Code Editing via Open-Source Language Models
Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact and avoiding unnecessary modifications. However, commit-based datasets commonly used for this task are often noisy, lack diversity, and fail to reflect the style of real-world edit instructions. To address this, we introduce CanItEdit, an open-source pipeline that leverages multiple LLMs to synthesize realistic code-e…

I notice that most people in my circles tend to gravitate toward OpenAI and Anthropic and tend to discount Google when it comes to Gen AI. This is pretty freakin' cool:
https://arstechnica.com/ai/2025/08/google-improves-gemini-ai-image-ed…

Google improves Gemini AI image editing with “nano banana” model
Gemini 2.5 Flash Image is currently atop LMArena’s image-editing leaderboard.

EditTrack: Detecting and Attributing AI-assisted Image Editing
Zhengyuan Jiang, Yuyang Zhang, Moyang Guo, Neil Zhenqiang Gong
https://arxiv.org/abs/2510.01173 https://

EditTrack: Detecting and Attributing AI-assisted Image Editing
In this work, we formulate and study the problem of image-editing detection and attribution: given a base image and a suspicious image, detection seeks to determine whether the suspicious image was derived from the base image using an AI editing model, while attribution further identifies the specific editing model responsible. Existing methods for detecting and attributing AI-generated images are insufficient for this problem, as they focus on determining whether an image was AI-generated/edit…

If I get any of the grants I applied for, I will do #live streams again for the #development. ✨👩‍💻✨
Thus far, I asked:
- NLnet to fund #LinuxBoot integration with U-Boot XPL
- OSFF to…

Editing Cotton Mather's Biblia Americana (1693-1728): America’s First Bible Commentary and Storehouse of Early Modern Learning https://networks.h-net.org/group/announcements/20121478/editing-cotton-mathers-biblia-am…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Jan Zdenek, Wataru Shimoda, Kota Yamaguchi
https://arxiv.org/abs/2510.02787 https://arxiv.org/pdf/2…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not ca…

Whee #KDEnlive is available for macOS and even Apple Silicon CPUs. During Project Rendering it seems make use of all the CPU core at least. Not the GPU though.

https://kdenlive.org

This must be the ultimate #monsterdon
- monster? Check
- nuclear terror? Check
- hip soundtrack? Check
- unbearably bad acting? Check
- unbearably bad writing? Check
- unbearably bad voice-over? Check
- unbearably bad editing? Check
- long sequences of irrelevant stock footage? Check
- bizarre plot twist you didn't expect? Check
- solid inspiration to any aspiring film maker who thinks they aren't good enough or have budget enough or skills enough to gain eternal global distribution? Check
What more could you want?
"Monster a Go-Go" (Herschell Gordon Lewis, 1965) - FULL MOVIE
https://youtube.com/watch?v=btJoXBIv2SI&si=nDLa-edc1VlFlerV

Let the SwiftUI graph editing begin!

Replaced article(s) found for cs.MM. https://arxiv.org/list/cs.MM/new
[1/1]:
- ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems
Chenxi Wang, Jizhan Fang, Xiang Chen, Bozhong Tian, Ziwen Xu, Huajun Chen, Ningyu Zhang

Security measures for Gen #AI seem to increase all around, which is overall good.
It's just sad to think about WHY statements like "Gemini 2.5 Flash Image does not currently support editing images of children" are necessary in the first place.
#nanobanana

REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Yisu Wang, Ming Wang, Haoyuan Song, Wenjie Huang, Chaozheng Wang, Yi Xie, Xuming Ran
https://arxiv.org/abs/2510.01879

REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce REPAIR (Robust Editing via Progressive Adaptive Intervention and Reintegration), a lifelong editing framework designed to support precise and low-cost model updates while preserving non-target knowledge. REPAIR mitigates the instability and conflicts of large-…

Anthropic adds context editing and a memory tool to the Claude API, allowing AI agents to handle long-running tasks without frequently hitting context limits (Anthropic)
https://www.anthropic.com/news/context-management

Managing context on the Claude Developer Platform
We're introducing new capabilities for managing your agents’ context on the Claude Developer Platform: context editing and the memory tool.

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han
https://arxiv.org/abs/2509.00918

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. Recent work has revealed that model editing in the fingerprinting domain offers distinct advantages, including significantly lower false positive rates, enhanced harmlessness, and su…

ISSE: An Instruction-Guided Speech Style Editing Dataset And Benchmark
Yun Chen, Qi Chen, Zheqi Dai, Arshdeep Singh, Philip J. B. Jackson, Mark D. Plumbley
https://arxiv.org/abs/2509.24570

ISSE: An Instruction-Guided Speech Style Editing Dataset And Benchmark
Speech style editing refers to modifying the stylistic properties of speech while preserving its linguistic content and speaker identity. However, most existing approaches depend on explicit labels or reference audio, which limits both flexibility and scalability. More recent attempts to use natural language descriptions remain constrained by oversimplified instructions and coarse style control. To address these limitations, we introduce an Instruction-guided Speech Style Editing Dataset (ISSE)…

An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs
Xinfang Chen, Siyang Xiao, Xianying Zhu, Junhong Xie, Ming Liang, Dajun Chen, Wei Jiang, Yong Li, Peng Di
https://arxiv.org/abs/2508.02473

An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs
Code editing, including modifying, refactoring, and maintaining existing code, is the most frequent task in software development and has garnered significant attention from AI-powered tools. However, existing solutions that translate explicit natural language instructions into code edits face critical limitations, such as heavy reliance on human instruction input and high latency, which hinder their effective integration into a developer's workflow. We observe that developers' habitual behavior…

4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
Lei Liu, Can Wang, Zhenghao Chen, Dong Xu
https://arxiv.org/abs/2510.01991 https://arx…

4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a consistent and interactive 4DGS editing framework. We first introduce a 4D-aware InstructPix2Pix model to ensure both view and temporal consistency. This model incorporates 4D VGGT geometry features extracted from the initial scene, enabling it to capture underl…

Challenge: "Name 20 female authors you admire, 1 per day"
Day 9:
Pat Cadigan
Sometimes called the godmother of Cyberpunk, her writing (and editing!) is much broader than that. An influential workhorse!
I particularly enjoyed her novel "Mindplayers" and the novelisation she wrote of William Gibson's screenplay for Alien3.
#FemmeÉcrivain…

Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency
https://qwenlm.github.io/blog/qwen-image-edit/?utm_source=www.the…

Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu, Jia-Chen Gu, Yunzhi Yao, Hong Wang, Nanyun Peng
https://arxiv.org/abs/2510.01172 https://

Energy-Regularized Sequential Model Editing on Hyperspheres
Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes representations and induces catastrophic forgetting. In this work, we seek to better understand and mitigate performance degradation caused by sequential editing. We hypothesize that hyperspherical uniformity, a property that maintains uniform distribution of neuron weights on a hypersp…

Not sure what I expected here, but Lightroom’s HDR editing support combined with its SDR rendition settings are consistently giving me the best results for highlight recovery. Just gives you more control, even for SDR output. #AdobeLightroom #Lightroom

Editing Cotton Mather's Biblia Americana (1693-1728): America’s First Bible Commentary and Storehouse of Early Modern Learning
https://ift.tt/OSGUehP
Pirino on Suzuki, 'Humanitarian Internationalism Under Empire: The Global Evolution of the Japanese…
via Input 4 RELCFP

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Wai-Kin Kong
https://arxiv.org/abs/2510.02253

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with flow matching (e.g., SD3.5, FLUX), generative priors have become significantly stronger, enabling advances across diverse editing tasks. However, drag-based editing has yet to benefit from these strong…

3D-LATTE: Latent Space 3D Editing from Textual Instructions
Maria Parelli, Michael Oechsle, Michael Niemeyer, Federico Tombari, Andreas Geiger
https://arxiv.org/abs/2509.00269 h…

3D-LATTE: Latent Space 3D Editing from Textual Instructions
Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality of generation models. The main reason is that recent approaches using 2D priors suffer from view-inconsistent editing signals. Going beyond 2D prior distillation methods and multi-view editing strategies, we propose a training-free editing method that operates within the latent space of a native 3D diffusion model, a…

Guiding Audio Editing with Audio Language Model
Zitong Lan, Yiduo Hao, Mingmin Zhao
https://arxiv.org/abs/2509.21625 https://arxiv.org/pdf/2509.21625

Guiding Audio Editing with Audio Language Model
Audio editing plays a central role in VR/AR immersion, virtual conferencing, sound design, and other interactive media. However, recent generative audio editing models depend on template-like instruction formats and are restricted to mono-channel audio. These models fail to deal with declarative audio editing, where the user declares what the desired outcome should be, while leaving the details of editing operations to the system. We introduce SmartDJ, a novel framework for stereo audio editing…

Understanding Collective Social Behavior in OSS Communities: A Co-editing Network Analysis of Activity Cascades
Lisi Qarkaxhija, Maximilian Carparo, Stefan Menzel, Bernhard Sendhoff, Ingo Scholtes
https://arxiv.org/abs/2509.26173

Understanding Collective Social Behavior in OSS Communities: A Co-editing Network Analysis of Activity Cascades
Understanding the collective social behavior of software developers is crucial to model and predict the long-term dynamics and sustainability of Open Source Software (OSS) communities. To this end, we analyze temporal activity patterns of developers, revealing an inherently ``bursty'' nature of commit contributions. To investigate the social mechanisms behind this phenomenon, we adopt a network-based modelling framework that captures developer interactions through co-editing networks. Our frame…

Adobe rolls out new generative AI features for Photoshop to let users more easily add or remove people and objects, including "Harmonize" compositing, in beta (Jess Weatherbed/The Verge)
https://www.theverge.com/news/715073/adobe-photosho…

Photoshop just made it shockingly easy to edit objects and people into photos
Adobe is launching some new generative AI features for Photoshop that make it easier than ever to convincingly add or remove people and objects in photographs.

Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
Kiymet Akdemir, Jing Shi, Kushal Kafle, Brian Price, Pinar Yanardag
https://arxiv.org/abs/2509.04446

Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
Text-to-image diffusion models have demonstrated significant capabilities to generate diverse and detailed visuals in various domains, and story visualization is emerging as a particularly promising application. However, as their use in real-world creative domains increases, the need for providing enhanced control, refinement, and the ability to modify images post-generation in a consistent manner becomes an important challenge. Existing methods often lack the flexibility to apply fine or coars…

Bilinear relational structure fixes reversal curse and enables consistent model editing
Dong-Kyum Kim, Minsung Kim, Jea Kwon, Nakyeong Yang, Meeyoung Cha
https://arxiv.org/abs/2509.21993

Bilinear relational structure fixes reversal curse and enables consistent model editing
The reversal curse -- a language model's (LM) inability to infer an unseen fact ``B is A'' from a learned fact ``A is B'' -- is widely considered a fundamental limitation. We show that this is not an inherent failure but an artifact of how models encode knowledge. By training LMs from scratch on a synthetic dataset of relational knowledge graphs, we demonstrate that bilinear relational structure emerges in their hidden representations. This structure substantially alleviates the reversal curse,…

Activation-Guided Local Editing for Jailbreaking Attacks
Jiecong Wang, Haoran Li, Hao Peng, Ziqian Zeng, Zihao Wang, Haohua Du, Zhengtao Yu
https://arxiv.org/abs/2508.00555 http…

Activation-Guided Local Editing for Jailbreaking Attacks
Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity. We propose a concise and effective two-stage framework that combines the advantages of these approaches. The …

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, Tianyidan Xie, Xiaokun Wang, Yichen Wei, Chuanxin Tang, Bo Zhu, Changshi Li, Hongyang Wei, Eric Li, Xuchen Song, Yang Liu, Yahui Zhou
https://arxiv.org/abs/2508.03320

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation r…

Physically Controllable Relighting of Photographs
Chris Careaga, Ya\u{g}{\i}z Aksoy
https://arxiv.org/abs/2508.05626 https://arxiv.org/pdf/2508.05626

Physically Controllable Relighting of Photographs
We present a self-supervised approach to in-the-wild image relighting that enables fully controllable, physically based illumination editing. We achieve this by combining the physical accuracy of traditional rendering with the photorealistic appearance made possible by neural rendering. Our pipeline works by inferring a colored mesh representation of a given scene using monocular estimates of geometry and intrinsic components. This representation allows users to define their desired illuminatio…

Google rolls out an AI-powered conversational photo editing tool, previously exclusive to the Pixel 10 series, to all Google Photos users on Android (Artie Beaty/ZDNET)
https://www.zdnet.com/article/android-users-just…

Your Android phone just got a massive Google Photos upgrade - here's what it can do now
Previously exclusive to the Pixel 10, you can now edit photos with a simple AI prompt - remove glare, add clouds, and more.

Paper2Video: Automatic Video Generation from Scientific Papers
Zeyu Zhu, Kevin Qinghong Lin, Mike Zheng Shou
https://arxiv.org/abs/2510.05096 https://arxiv…

Paper2Video: Automatic Video Generation from Scientific Papers
Academic presentation videos have become an essential medium for research communication, yet producing them remains highly labor-intensive, often requiring hours of slide design, recording, and editing for a short 2 to 10 minutes video. Unlike natural video, presentation video generation involves distinctive challenges: inputs from research papers, dense multi-modal information (text, figures, tables), and the need to coordinate multiple aligned channels such as slides, subtitles, speech, and h…

From Editor to Dense Geometry Estimator
JiYuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao
https://arxiv.org/abs/2509.04338

From Editor to Dense Geometry Estimator
Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I generative models, may be a more suitable foundation for fine-tuning. Motivated by this, we conduct a systematic analysis of the fine-tuning behaviors of both editors and generators for dense geometry estimation. Our findings show that editing models possess i…

Exploring Diffusion Models for Generative Forecasting of Financial Charts
Taegyeong Lee, Jiwon Park, Kyunga Bang, Seunghyun Hwang, Ung-Jin Jang
https://arxiv.org/abs/2509.02308 …

Exploring Diffusion Models for Generative Forecasting of Financial Charts
Recent advances in generative models have enabled significant progress in tasks such as generating and editing images from text, as well as creating videos from text prompts, and these methods are being applied across various fields. However, in the financial domain, there may still be a reliance on time-series data and a continued focus on transformer models, rather than on diverse applications of generative models. In this paper, we propose a novel approach that leverages text-to-image model …

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, Wei Tsang Ooi
https://arxiv.org/abs/2508.03692

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dynamic 4D world modeling presents challenges in controllability, temporal coherence, and evaluation standardization. To this end, we present LiDARCrafter, a unified framework for 4D LiDAR generation and editing. Given free-form natural language inputs, we parse instructions into eg…

Does Editing Improve Answer Quality on Stack Overflow? A Data-Driven Investigation
Saikat Mondal, Chanchal K. Roy
https://arxiv.org/abs/2507.21329 https://…

Does Editing Improve Answer Quality on Stack Overflow? A Data-Driven Investigation
High-quality answers in technical Q&A platforms like Stack Overflow (SO) are crucial as they directly influence software development practices. Poor-quality answers can introduce inefficiencies, bugs, and security vulnerabilities, and thus increase maintenance costs and technical debt in production software. To improve content quality, SO allows collaborative editing, where users revise answers to enhance clarity, correctness, and formatting. Several studies have examined rejected edits and ide…

LatentEdit: Adaptive Latent Control for Consistent Semantic Editing
Siyi Liu, Weiming Chen, Yushun Tang, Zhihai He
https://arxiv.org/abs/2509.00541 https://

LatentEdit: Adaptive Latent Control for Consistent Semantic Editing
Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory efficiency. In this work, we introduce LatentEdit, an adaptive latent fusion framework that dynamically combines the current latent code with a reference latent code inverted from the source image. By selectively preserving source features in high-similarity, semantica…

Google says Gemini 2.5 Flash Image, aka Nano Banana, is now generally available and supports more aspect ratios, priced at $0.039/image and $30/1M output tokens (Google Developers Blog)
https://developers.googleblog.com/en/gemini-2…

Gemini 2.5 Flash Image now ready for production with new aspect ratios- Google Developers Blog
Our state-of-the-art image generation and editing model which has captured the imagination of the wo...

Editing Cotton Mather's Biblia Americana (1693-1728): America’s First Bible Commentary and Storehouse of Early Modern Learning
https://ift.tt/CbUHYMX
Pirino on Suzuki, 'Humanitarian Internationalism Under Empire: The Global Evolution of the Japanese…
via Input 4 RELCFP

Virtual Consistency for Audio Editing
Matthieu Cervera, Francesco Paissan, Mirco Ravanelli, Cem Subakan
https://arxiv.org/abs/2509.17219 https://arxiv.org/…

Virtual Consistency for Audio Editing
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Cr…

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
Seunghoo Hong, Geonho Son, Juhun Lee, Simon S. Woo
https://arxiv.org/abs/2510.00778 https://

DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A direct inheriting application of this inversion operation is real image editing, where the inversion yields latent trajectories to be utilized during the synthesis of the edited image. Unfortunately, this practical tool has enabled malicious users to freely …

FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models
Likun Tan, Kuan-Wei Huang, Kevin Wu
https://arxiv.org/abs/2507.20930 https://

FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models
Hallucinations in large language models pose a critical challenge for applications requiring factual reliability, particularly in high-stakes domains such as finance. This work presents an effective approach for detecting and editing factually incorrect content in model-generated responses based on the provided context. Given a user-defined domain-specific error taxonomy, we construct a synthetic dataset by inserting tagged errors into financial question-answering corpora and then fine-tune fou…

RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing
Liting Gao, Yi Yuan, Yaru Chen, Yuelan Cheng, Zhenbo Li, Juan Wen, Shubin Zhang, Wenwu Wang
https://arxiv.org/abs/2509.14003

RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing
Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest, thus demanding precise localization and faithful editing according to the text prompt. Existing training-based and zero-shot methods that rely on full-caption or costly optimization often struggle with complex editing or lack practicality. In this work, we p…

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
Mohammad Aflah Khan, Ameya Godbole, Johnny Tian-Zheng Wei, Ryan Wang, James Flemings, Krishna Gummadi, Willie Neiswanger, Robin Jia
https://arxiv.org/abs/2507.19419

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
Understanding the relationship between training data and model behavior during pretraining is crucial, but existing workflows make this process cumbersome, fragmented, and often inaccessible to researchers. We present TokenSmith, an open-source library for interactive editing, inspection, and analysis of datasets used in Megatron-style pretraining frameworks such as GPT-NeoX, Megatron, and NVIDIA NeMo. TokenSmith supports a wide range of operations including searching, viewing, ingesting, expor…

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Keming Wu, Sicong Jiang, Max Ku, Ping Nie, Minghao Liu, Wenhu Chen
https://arxiv.org/abs/2509.26346

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source models are still lagging. The main bottleneck is the lack of a reliable reward model to scale up high-quality synthetic training data. To address this critical bottleneck, we built \mname, trained with our new large-scale human preference dataset, meticulously…

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
Yuxin Song, Wenkai Dong, Shizun Wang, Qi Zhang, Song Xue, Tao Yuan, Hu Yang, Haocheng Feng, Hang Zhou, Xinyan Xiao, Jingdong Wang
https://arxiv.org/abs/2509.26641

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with diffusion-based generator, or as naive Unified Multimodal Models with an early fusion of understanding and generation modalities. We contend that in current unified frameworks, the crucial capability of multimodal generative reasoning which encompasses instructio…

Setting The Table with Intent: Intent-aware Schema Generation and Editing for Literature Review Tables
Vishakh Padmakumar, Joseph Chee Chang, Kyle Lo, Doug Downey, Aakanksha Naik
https://arxiv.org/abs/2507.19521

Setting The Table with Intent: Intent-aware Schema Generation and Editing for Literature Review Tables
The increasing volume of academic literature makes it essential for researchers to organize, compare, and contrast collections of documents. Large language models (LLMs) can support this process by generating schemas defining shared aspects along which to compare papers. However, progress on schema generation has been slow due to: (i) ambiguity in reference-based evaluations, and (ii) lack of editing/refinement methods. Our work is the first to address both issues. First, we present an approach…

3DiFACE: Synthesizing and Editing Holistic 3D Facial Animation
Balamurugan Thambiraja, Malte Prinzler, Sadegh Aliakbarian, Darren Cosker, Justus Thies
https://arxiv.org/abs/2509.26233

3DiFACE: Synthesizing and Editing Holistic 3D Facial Animation
Creating personalized 3D animations with precise control and realistic head motions remains challenging for current speech-driven 3D facial animation methods. Editing these animations is especially complex and time consuming, requires precise control and typically handled by highly skilled animators. Most existing works focus on controlling style or emotion of the synthesized animation and cannot edit/regenerate parts of an input animation. They also overlook the fact that multiple plausible li…

Google updates video editing tool Vids to add AI avatars, automatic transcript trimming, and image-to-video tools, and releases a basic version to all users (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/08/27/google-vid…

Google Vids adds AI avatars to its video editor and launches a consumer version | TechCrunch
Google is launching a free consumer version of its video editor Vids that will be available without any AI-powered features.

CAMILA: Context-Aware Masking for Image Editing with Language Alignment
Hyunseung Kim, Chiho Choi, Srikanth Malla, Sai Prahladh Padmanabhan, Saurabh Bagchi, Joon Hee Choi
https://arxiv.org/abs/2509.19731

CAMILA: Context-Aware Masking for Image Editing with Language Alignment
Text-guided image editing has been allowing users to transform and synthesize images through natural language instructions, offering considerable flexibility. However, most existing image editing models naively attempt to follow all user instructions, even if those instructions are inherently infeasible or contradictory, often resulting in nonsensical output. To address these challenges, we propose a context-aware method for image editing named as CAMILA (Context-Aware Masking for Image Editing…

SpotEdit: Evaluating Visually-Guided Image Editing Methods
Sara Ghazanfari, Wei-An Lin, Haitong Tian, Ersin Yumer
https://arxiv.org/abs/2508.18159 https://…

SpotEdit: Evaluating Visually-Guided Image Editing Methods
Visually-guided image editing, where edits are conditioned on both visual cues and textual prompts, has emerged as a powerful paradigm for fine-grained, controllable content generation. Although recent generative models have shown remarkable capabilities, existing evaluations remain simple and insufficiently representative of real-world editing challenges. We present SpotEdit, a comprehensive benchmark designed to systematically assess visually-guided image editing methods across diverse diffus…

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Xuan Ju, Tianyu Wang, Yuqian Zhou, He Zhang, Qing Liu, Nanxuan Zhao, Zhifei Zhang, Yijun Li, Yuanhao Cai, Shaoteng Liu, Daniil Pakhomov, Zhe Lin, Soo Ye Kim, Qiang Xu
https://arxiv.org/abs/2509.20360

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified frameworks, video generation and editing remain fragmented due to architectural limitations and data scarcity. In this work, we introduce EditVerse, a unified framework for image and video generation and editing within a single model. By representing all modali…

ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
Xiang Tang, Ruotong Li, Xiaopeng Fan
https://arxiv.org/abs/2509.23607

ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
In the field of 3D content generation, single image scene reconstruction methods still struggle to simultaneously ensure the quality of individual assets and the coherence of the overall scene in complex environments, while texture editing techniques often fail to maintain both local continuity and multi-view consistency. In this paper, we propose a novel system ZeroScene, which leverages the prior knowledge of large vision models to accomplish both single image-to-3D scene reconstruction and t…

VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Lin Li, Zehuan Huang, Haoran Feng, Gengxiong Zhuang, Rui Chen, Chunchao Guo, Lu Sheng
https://arxiv.org/abs/2508.19247

VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory an…

Editing Physiological Signals in Videos Using Latent Representations
Tianwen Zhou, Akshay Paruchuri, Josef Spjut, Kaan Ak\c{s}it
https://arxiv.org/abs/2509.25348 https://…

Editing Physiological Signals in Videos Using Latent Representations
Camera-based physiological signal estimation provides a non-contact and convenient means to monitor Heart Rate (HR). However, the presence of vital signals in facial videos raises significant privacy concerns, as they can reveal sensitive personal information related to the health and emotional states of an individual. To address this, we propose a learned framework that edits physiological signals in videos while preserving visual fidelity. First, we encode an input video into a latent space v…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- Training-free Geometric Image Editing on Diffusion Models
Hanshen Zhu, Zhen Zhu, Kaile Zhang, Yiming Gong, Yuliang Liu, Xiang Bai

AnchorSync: Global Consistency Optimization for Long Video Editing
Zichi Liu, Yinggui Wang, Tao Wei, Chao Ma
https://arxiv.org/abs/2508.14609 https://arxiv…

AnchorSync: Global Consistency Optimization for Long Video Editing
Editing long videos remains a challenging task due to the need for maintaining both global consistency and temporal coherence across thousands of frames. Existing methods often suffer from structural drift or temporal artifacts, particularly in minute-long sequences. We introduce AnchorSync, a novel diffusion-based framework that enables high-quality, long-term video editing by decoupling the task into sparse anchor frame editing and smooth intermediate frame interpolation. Our approach enforce…

AutoEdit: Automatic Hyperparameter Tuning for Image Editing
Chau Pham, Quan Dao, Mahesh Bhosale, Yunjie Tian, Dimitris Metaxas, David Doermann
https://arxiv.org/abs/2509.15031 h…

AutoEdit: Automatic Hyperparameter Tuning for Image Editing
Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get the reasonable editing performance, these methods often require the user to brute-force tune multiple interdependent hyperparameters, such as inversion timesteps and attention modification, \textit{etc.} This process incurs high computational costs due to the huge hyperparameter search space. We consider searching optim…

Visual Autoregressive Modeling for Instruction-Guided Image Editing
Qingyang Mao, Qi Cai, Yehao Li, Yingwei Pan, Mingyue Cheng, Ting Yao, Qi Liu, Tao Mei
https://arxiv.org/abs/2508.15772

Visual Autoregressive Modeling for Instruction-Guided Image Editing
Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to unintended spurious modifications and compromised adherence to editing instructions. In contrast, autoregressive models offer a distinct paradigm by formulating image synthesis as a sequential process over discrete visual tokens. Their causal and compositional mech…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/9]:
- Diagnosing Reliability in Text-Guided Medical Image Editing
Minghao Liu, Zhitao He, Zhiyuan Fan, Qingyun Wang, Yi R. Fung

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Yiyang Chen, Xuanhua He, Xiujun Ma, Yue Ma
https://arxiv.org/abs/2509.17818 https://

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing methods, often designed for U-Net architectures, suffer from two primary limitations: inaccurate inversion due to first-order solvers, and contextual conflicts caused by crude "hard" feature replacement. These issues are more challenging in Diffusion Transforme…

InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior
Minghao Wen, Shengjie Wu, Kangkan Wang, Dong Liang
https://arxiv.org/abs/2507.04961

InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior
3D Gaussian Splatting based 3D editing has demonstrated impressive performance in recent years. However, the multi-view editing often exhibits significant local inconsistency, especially in areas of non-rigid deformation, which lead to local artifacts, texture blurring, or semantic variations in edited 3D scenes. We also found that the existing editing methods, which rely entirely on text prompts make the editing process a "one-shot deal", making it difficult for users to control the editing de…

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Yuhan Wang, Siwei Yang, Bingchen Zhao, Letian Zhang, Qing Liu, Yuyin Zhou, Cihang Xie
https://arxiv.org/abs/2507.21033

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct …

CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion
Zhe Zhu, Honghua Chen, Peng Li, Mingqiang Wei
https://arxiv.org/abs/2508.11603 https://

CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion
Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view information exchange, they often fail to maintain cross-view consistency, leading to insufficient edits and blurry details. We introduce CoreEditor, a novel framework for consistent text-to-3D editing. The key innovation is a correspondence-constrained attentio…

IMAGEdit: Let Any Subject Transform
Fei Shen, Weihao Xu, Rui Yan, Dong Zhang, Xiangbo Shu, Jinhui Tang
https://arxiv.org/abs/2510.01186 https://arxiv.org/p…

IMAGEdit: Let Any Subject Transform
In this paper, we present IMAGEdit, a training-free framework for any number of video subject editing that manipulates the appearances of multiple designated subjects while preserving non-target regions, without finetuning or retraining. We achieve this by providing robust multimodal conditioning and precise mask sequences through a prompt-guided multimodal alignment module and a prior-based mask retargeting module. We first leverage large models' understanding and generation capabilities to pr…

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
Zixin Yin, Xili Dai, Duomin Wang, Xianfang Zeng, Lionel M. Ni, Gang Yu, Heung-Yeung Shum
https://arxiv.org/abs/2509.12203

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and costly test-time optimization (TTO). This compromise severely limits the generative capabilities of diffusion models, suppressing high-fidelity inpainting and text-guided creation. In this paper, we introduce LazyDrag, the first drag-based image editing method for Multi-Modal Diffusion Transformers, which directly elim…

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Matteo Trippodo, Federico Becattini, Lorenzo Seidenari
https://arxiv.org/abs/2509.10359 https://

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that targets the visual component of editing methods. We introduce Attention Attack, which disrupts the cross-attention between a textual prompt and the visual representation of the image by using an automatically generated caption of the source image as a proxy for t…

Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
Jiarong Ye, Sharon X. Huang
https://arxiv.org/abs/2507.14024 https://arxiv.org/…

Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
Bridging emotions and visual content for emotion-driven image editing holds great potential in creative industries, yet precise manipulation remains challenging due to the abstract nature of emotions and their varied manifestations across different contexts. We tackle this challenge with an integrated approach consisting of three complementary components. First, we introduce MoodArchive, an 8M+ image dataset with detailed hierarchical emotional annotations generated by LLaVA and partially valid…

NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining
Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh, Georgii Fedorov, Bulat Suleimanov, Vladimir Dokholyan, Aleksandr Gordeev
https://arxiv.org/abs/2507.14119

NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining
Recent advances in generative modeling enable image editing assistants that follow natural language instructions without additional user input. Their supervised training requires millions of triplets: original image, instruction, edited image. Yet mining pixel-accurate examples is hard. Each edit must affect only prompt-specified regions, preserve stylistic coherence, respect physical plausibility, and retain visual appeal. The lack of robust automated edit-quality metrics hinders reliable auto…