Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works19 from public data
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation1,235
This work proposes a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented, and introduces Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy.
- DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models193
This paper builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation, and shows that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module.
- 135
- Long-Context Autoregressive Video Modeling with Next-Frame Prediction126
This paper proposes the long short-term context modeling using asymmetric patchify kernels, which apply large kernels to distant frames to reduce redundant tokens, and standard kernels to local frames to preserve fine-grained detail, providing an effective baseline for long-context autoregressive video modeling.
- VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence81
This work introduces the Video Swap framework that exploits semantic point correspondences, inspired by the observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape.
- Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis37
It is found that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation, instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures.
- MIND: Benchmarking Memory Consistency and Action Control in World Models29
This work designs an efficient evaluation framework to measure two core abilities: memory consistency and action control, capturing temporal stability and contextual coherence across viewpoints and introduces MIND, the first open-domain closed-loop revisited benchmark for evaluating Memory stability and action control in worlD models.
- MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance29
MAG-Edit is proposed, a plug-and-play, inference-stage optimization method that empowers attention-based editing approaches, such as P2P, to enhance localized image editing in intricate scenarios and optimizes the noise latent feature by encouraging two mask-based cross-attention ratios of the edit token.
- 25
- Personalized Vision via Visual In-Context Learning17
This work introduces Personalized In-Context Operator (PICO), a simple four-panel framework that repurposes diffusion transformers as visual in-context learners that surpasses fine-tuning and synthetic-data baselines, flexibly adapts to novel user-defined tasks, and generalizes across both recognition and generation.
- MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers14
An efficient model called MaskINT is introduced, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the edited keyframes, using the structural guidance from intermediate frames.
- Point Cloud Segmentation Algorithm Based on Improved Euclidean Clustering11
To address the issue of over-segmentation and under-segmentation in cases of object adhesion and stacking in unordered scenes, a method is introduced for discriminating collision points based on normal angle constraints and an adaptive search radius is employed to determine the clustering distance threshold.
- Olaf-World: Orienting Latent Actions for Video World Modeling9
Olaf-World is presented, a pipeline that pretrains action-conditioned video world models from large-scale passive video and learns a more structured latent action space, leading to stronger zero-shot action transfer and more data-efficient adaptation to new control interfaces than state-of-the-art baselines.
- ROICtrl: Boosting Instance Control for Visual Generation9
This work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption, and proposes ROICtrl, an adapter for pretrained diffusion models that enables precise regional instance control.
- Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model3
This work introduces UnifyEdit, a tuning-free method that performs diffusion latent optimization to enable a balanced integration of fidelity and editability within a unified framework, demonstrating its superiority in achieving a robust balance between structure preservation and text alignment across various editing tasks.
- 2
- 1
- 1
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.