Image de couverture de livre

SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Song, Yiren, Wang, Yihan, Deng, Xiyao, Yan, Zhuoran, Shou, Mike Zheng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
par: Song, Yiren, et autres
Publié: (2026)

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
par: Shi, Yiqing, et autres
Publié: (2025)

DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
par: Song, Yiren, et autres
Publié: (2024)

WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation
par: Song, Quanjian, et autres
Publié: (2025)

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data
par: Huang, Shijie, et autres
Publié: (2025)

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
par: Song, Yiren, et autres
Publié: (2025)

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
par: Song, Yiren, et autres
Publié: (2025)

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
par: Song, Yiren, et autres
Publié: (2025)

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
par: Song, Yiren, et autres
Publié: (2024)

VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers
par: Song, Yiren, et autres
Publié: (2026)

OmniPSD: Layered PSD Generation with Diffusion Transformer
par: Liu, Cheng, et autres
Publié: (2025)

StreamingEffect: Real-Time Human-Centric Video Effect Generation
par: Song, Yiren, et autres
Publié: (2026)

Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?
par: Yang, Pei, et autres
Publié: (2024)

Mitty: Diffusion-based Human-to-Robot Video Generation
par: Song, Yiren, et autres
Publié: (2025)

X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale
par: Yang, Pei, et autres
Publié: (2025)

RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification
par: Ci, Hai, et autres
Publié: (2024)

Edit Transfer: Learning Image Editing via Vision In-Context Relations
par: Chen, Lan, et autres
Publié: (2025)

UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining
par: Yang, Pei, et autres
Publié: (2026)

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration
par: Song, Yiren, et autres
Publié: (2026)

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
par: Mao, Qi, et autres
Publié: (2025)

WMAdapter: Adding WaterMark Control to Latent Diffusion Models
par: Ci, Hai, et autres
Publié: (2024)

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment
par: Ouyang, Ziheng, et autres
Publié: (2025)

Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
par: Zeng, Ziyun, et autres
Publié: (2025)

Personalized Vision via Visual In-Context Learning
par: Jiang, Yuxin, et autres
Publié: (2025)

SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
par: He, Ziheng, et autres
Publié: (2026)

Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions
par: Zhao, Bo, et autres
Publié: (2026)

Bootstrapping SparseFormers from Vision Foundation Models
par: Gao, Ziteng, et autres
Publié: (2023)

H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
par: Ci, Hai, et autres
Publié: (2025)

TPDiff: Temporal Pyramid Video Diffusion Model
par: Ran, Lingmin, et autres
Publié: (2025)

D-AR: Diffusion via Autoregressive Models
par: Gao, Ziteng, et autres
Publié: (2025)

Ego-centric Predictive Model Conditioned on Hand Trajectories
par: Zhang, Binjie, et autres
Publié: (2025)

World Action Models: The Next Frontier in Embodied AI
par: Wang, Siyin, et autres
Publié: (2026)

PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
par: Gao, Heyuan, et autres
Publié: (2026)

Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation
par: Song, Yiren, et autres
Publié: (2024)

EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing
par: Chen, Lan, et autres
Publié: (2026)

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
par: Deng, Yueci, et autres
Publié: (2026)

Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
par: Liu, Yepeng, et autres
Publié: (2024)

VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
par: Lin, Kevin Qinghong, et autres
Publié: (2025)

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
par: Liang, Dingkang, et autres
Publié: (2025)

Accurate Forgetting for All-in-One Image Restoration Model
par: Su, Xin, et autres
Publié: (2024)