Goto

Collaborating Authors

 Media


SceneDesigner: Controllable Multi-Object Image Generation with 9-DoFPose Manipulation

Neural Information Processing Systems

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose SceneDesigner, a method for accurate and flexible multi-object 9-DoF pose manipulation. SceneDesigner incorporates a branched network to the pre-trained base model and leverages a new representation, CNOCS map, which encodes 9D pose information from the camera view.



FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing

Neural Information Processing Systems

Latent Diffusion-based Text-to-Image (T2I) is a free image editing tool that typically reverses an image into noise, reconstructs it using its original text prompt, and then generates an edited version under a new target prompt. To preserve unaltered image content, features from the reconstruction are directly injected to replace selected features in the generation. However, this direct replacement often leads to feature incompatibility, compromising editing fidelity and limiting creative flexibility, particularly for non-rigid edits (e.g., structural or pose changes). In this paper, we aim to address these limitations by proposing FSI-Edit, a novel framework using frequency-and stochasticity-based feature injection for flexible image editing. First, FSI-Edit enhances feature consistency by injecting high-frequency components of reconstruction features into generation features, mitigating incompatibility while preserving the editing ability for major structures encoded in low-frequency information. Second, it introduces controlled noise into the replaced reconstruction features, expanding the generative space to enable diverse non-rigid edits beyond the original image's constraints. Experiments on non-rigid edits, e.g., addition, deletion, and pose manipulation, demonstrate that FSI-Edit outperforms existing baselines in target alignment, semantic fidelity and visual quality. Our work highlights the critical roles of frequency-aware design and stochasticity in overcoming rigidity in diffusion-based editing.


Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction

Neural Information Processing Systems

Information diffusion prediction, which aims to forecast the future infected users during the information spreading process on social platforms, is a challenging and critical task for public opinion analysis. With the development of social platforms, mass communication has become increasingly widespread. However, most existing methods based on GNNs and sequence models mainly focus on structural and temporal patterns in social networks, suffering from spurious diffusion connections and insufficient information for diffusion analysis. We leverage the strong reasoning capabilities of LLMs and develop an LLM-based causal framework for diffusion influence derivation, named MILD. By comprehensively integrating four key factors of social diffusion--i.e., connections, active timelines, user profiles, and comments--MILD causally infers authentic diffusion links to construct a diffusion influence graph, GI. To validate the quality and reliability of our constructed graph GI, we propose a newly designed set of evaluation metrics for diffusion prediction. In experiments, MILD provides a reliable information diffusion structure that achieves an absolute improvement of 12% over the social network structure and achieves state-of-the-art performance in diffusion prediction. MILD is expected to contribute to higher-quality, more explainable, and more trustworthy public opinion analysis. The code and data are available at: https://github.com/Shang-hub/


LayerCraft: Enhancing Text-to-Image Generation with CoTReasoning and Layered Object Integration

Neural Information Processing Systems

Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multistep editing. We present LayerCraft, a modular framework that uses large language models (LLMs) as autonomous agents to orchestrate structured, layered image generation and editing. LayerCraft supports two key capabilities: (1) structured generation from simple prompts via chain-of-thought (CoT) reasoning, enabling it to decompose scenes, reason about object placement, and guide composition in a controllable, interpretable manner; and (2) layered object integration, allowing users to insert and customize objects--such as characters or props--across diverse images or scenes while preserving identity, context, and style. The system comprises a coordinator agent, the ChainArchitect for CoT-driven layout planning, and the Object Integration Network (OIN) for seamless image editing using off-the-shelf T2I models without retraining. Through applications like batch collage editing and narrative scene generation, LayerCraft empowers non-experts to iteratively design, customize, and refine visual content with minimal manual effort.


Dynamic View Synthesis as an Inverse Problem

Neural Information Processing Systems

We begin by identifying terminal signal-to-noise a fundamental ratio obstacle (SNR) schedules to deterministic and resolv inv e ersion it by introducing arising from a no zerovel noise representation, termed K-order Recursive Noise Representation.


ImgEdit: AUnified Image Editing Dataset and Benchmark

Neural Information Processing Systems

Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce ImgEdit, a largescale, high-quality image-editing dataset comprising one million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks. To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict postprocessing.


Scientists predict how the world will end - and say Earth may NOT be swallowed by the sun after all

Daily Mail - Science & tech

Trump declares that Keir Starmer'failed badly' as UK's Prime Minister as he CRIES while resigning Boston's Scotland-loving residents claim England fans are'ruining the vibe' compared to the Tartan Army'Al Roker is an absolute ****': KENNEDY's Today show insider gives brutal behind-the-scenes verdict on beloved weatherman and names other two-faced NBC hosts Call me cynical, but the real reason Gruesome Twosome Harry and Meghan are returning to the UK is just so obvious... and highly humiliating: MAUREEN CALLAHAN Putin'prepares mass call-up' for the Ukraine meat-grinder - as video shows Russian veteran with no legs threatening recruiter with a knife in sign of growing resistance facing desperate Kremlin Secret life of John Travolta's daughter Ella Bleu: New details about'unusual' relationship with her dad revealed by insiders amid fears that aspiring actress is'stuck' Johnny Depp's ex Amber Heard gives rare glimpse of daughter Oonagh, five, after finishing 10k race in Spain Rock band playing at Madison Square Garden when fan, 51, plunged to his death break silence... as investigators probe his final moments Colorado siblings VANISH from home in middle of the night... and police still can't find them a week later Revealed: Emotional handwritten letter Iran's'oppressed' World Cup stars left in SoFi Stadium locker room No one can see the real reason Jelly Roll divorced Bunnie XO. New footage shows tourists fleeing with their bags as fire destroys Dominican Republic resort - and it's revealed Italian celebrity died from carbon monoxide fumes Unseen trove of intimate letters from Nicole Brown Simpson's passionate affair: Her lover reveals jealous OJ's peeping tom compulsion and relentless stalking Map reveals every state's favorite fast food cheeseburger Family-man facade of award-winning children's swim coach is shattered by disturbing teen babysitter claims: Read all the vile texts Fidel Castro's'secret' daughter speaks out to reveal truth about those Justin Trudeau'sibling' rumors: 'Sensitive subject' Kyle Busch's widow posts heartbreaking Father's Day tribute a month on from his shock death at 41: 'Cards were already made' US marks'encouraging progress' in peace talks with Iran after summit was nearly derailed by Trump's fiery threat I'm 52, and after ending my sexless marriage I slept with men in every decade from 30s to 60s. Here's EXACTLY what happened with each of them and the surprising truth about who was best - and worst! For years, it's been believed that the sun will start to expand in around five billion years, swallowing our planet in the process. However, a new study suggests that this might not be the case after all.


Humanoid robots just got a workplace safety system

FOX News

NVIDIA introduces Halos for Robotics, which the company calls the industry's first full-stack safety system for robotics and physical AI operating near people.


How to stop scam texts from targeting aging parents

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG . Artemis crew says they wanted to'connect with humanity,' show what can be done when they put their mind to it Scientists revive ancient 24,000-year-old'zombie worm' from Arctic ice -- then it reproduced'Gigantic' ancient octopus used jaws to crush prey and hunted alongside the dinosaurs 100M years ago: study Scientists uncover identity of mysterious'golden orb' discovered miles underwater in 2023 Artemis astronauts enter eerie 40-minute communication blackout on Moon's far side NASA chief Jared Isaacman says Artemis II would not be possible'if it wasn't for President Trump' Researchers pinpoint source of black hole's 3,000-light-year-long jet stream using enhanced telescope network Is Spielberg's new UFO film more fact than fiction? Auburn University's bald eagle tradition celebrates its 25th anniversary American public'can handle' truth about UAPs, whistleblower says Google's AI unleashes new powerful scam-busting features for Android The CyberGuy explains steps you can take to protect yourself from scams. Scam texts are annoying for everyone.