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
- Jiashi FengSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works42 from public data
- MagicVideo: Efficient Video Generation With Latent Diffusion Models517
An efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo, which can generate smooth video clips that are concordant with the given text descriptions and proposes a novel VideoVAE auto-encoder for better RGB reconstruction.
- MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model426
This work introduces Magic/snimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity, and outperforms the strongest baseline on the challenging TikTok dancing dataset.
- DragDiffusion: Harnessing Diffusion Models for Interactive Point-Based Image Editing393
This work introduces two additional techniques, namely identity-preserving fine-tuning and reference-latent-control, to further preserve the identity of the original image and presents a challenging benchmark dataset called DRAGBENCH─ the first benchmark to evaluate the performance of interactive point-based image editing methods.
- Recovering the Unbiased Scene Graphs from the Biased Ones139
This paper shows that, due to the missing labels, SGG can be viewed as a "Learning from Positive and Unlabeled data" (PU learning) problem, where the reporting bias can be removed by recovering the unbiased probabilities from the biased ones by utilizing label frequencies.
- MagicEdit: High-Fidelity and Temporally Coherent Video Editing83
It is found that high-fidelity and temporally coherent video-to-video translation can be achieved by explicitly disentangling the learning of content, structure and motion signals during training.
- MagicMix: Semantic Mixing with Diffusion Models82
MagicMix is presented, a simple yet effective solution based on pre-trained text-conditioned diffusion models that does not require any spatial mask or re-training, yet is able to synthesize novel objects with high fidelity.
- 79
- Modeling Trajectories with Neural Ordinary Differential Equations69
A novel method entitled TrajODE is devised that combines the continuous-time characteristic of Neural Ordinary Differential Equations (ODE) with the robustness of stochastic latent spaces for more natural modeling of trajectories.
- DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention63
This paper aims to incorporate the sub-quadratic modeling capability of Gated Linear Attention (GLA) into the 2D diffusion backbone, and introduces Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead.
- MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation63
This work introduces MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline that can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness.
- Adversarial Domain Adaptation With Prototype-Based Normalized Output Conditioner45
This work improves concatenation conditioning by normalizing the output predictions to have the same norm of features, and term the derived method as Normalized OutpUt coNditioner (NOUN), and proposes to condition the cross-domain feature alignment in the prototype space rather than in the output space.
- Deep Learning-Guided Fiberoptic Raman Spectroscopy Enables Real-Time In Vivo Diagnosis and Assessment of Nasopharyngeal Carcinoma and Post-treatment Efficacy during Endoscopy42
A deep learning-guided fiberoptic Raman diagnostic platform is developed to assess its ability of real-time in vivo nasopharyngeal carcinoma diagnosis and post-treatment follow-up of NPC patients, and the saliency map of the best RS-CNN models using the correctly predicted Raman spectra is investigated.
- 39
- 25
- OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs24
OfTSR is introduced, a novel flow-based framework for one-step image super-resolution that can produce outputs with tunable levels of fidelity and realism and achieves state-of-the-art performance for one-step image super-resolution, while having the ability to flexibly tune the fidelity-realism trade-off.
- MagicAvatar: Multimodal Avatar Generation and Animation24
The flexibility of MagicAvatar is demonstrated through various applications, including text-guided and video-guided avatar generation, as well as multimodal avatar animation, which enables the animation of the provided human identity according to the specific motion derived from the first stage.
- ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance22
ClassDiffusion is presented, a technique that leverages a **semantic preservation loss** to explicitly regulate the concept space when learning a new concept and effectively improves the compositional abilities of fine-tuning models.
- Towards Adversarially Robust Deep Image Denoising22
It is found that existing DIDs are vulnerable to the adversarial noise generated by OBSATK, and an adversarial training strategy that jointly trains DIDs with adversarial and non-adversarial noisy data can recover high-quality clean images from real-world noise even without training on real noisy data.
- MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation19
Overall, MagicProp combines the flexibility of image-editing techniques with the superior temporal consistency of autoregressive modeling, enabling flexible editing of object types and aesthetic styles in arbitrary regions of input videos while maintaining good temporal consistency across frames.
- PANDA: Prototypical Unsupervised Domain Adaptation.14
This work attempts to calibrate the noisy pseudo labels with prototypes, and develops an unified framework termed PrototypicAl uNsupervised Domain Adaptation (PANDA) for UDA, which achieves state-of-the-art or competitive results on multiple UDA benchmarks including both object recognition and semantic segmentation tasks.
- AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models13
A novel method AdjointDPM is proposed, which first generates new samples from diffusion models by solving the corresponding probability-flow ODEs and uses the adjoint sensitivity method to backpropagate the gradients of the loss to the models' parameters by solving another augmented ODE.
- 12
- 11
- Accelerating Video Diffusion Models via Distribution Matching10
This work introduces a novel framework for diffusion distillation and distribution matching that dramatically reduces the number of inference steps while maintaining-and potentially improving-generation quality.
- Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method10
Symplectic Adjoint Guidance (SAG) is proposed, which calculates the gradient guidance in two inner stages and generates images with higher qualities compared to the baselines in both guided image and video generation tasks.
- Learning a robust foundation model against clean-label data poisoning attacks at downstream tasks9
This work proposes a defense strategy that significantly reduces the success rate of various data poisoning attacks in downstream tasks and aims to pre-train a robust foundation model by reducing adversarial feature distance and increasing inter-class feature distance.
- 5
- MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution3
Experiments on both synthetic and real-world benchmarks demonstrate that MFSR achieves efficient, flexible, and high-quality super-resolution, delivering results on par with or even better than multi-step teachers while requiring much lower computational cost.
- StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents3
Grounding action, verification, and memory in state, what the authors call state-grounding, shifts the main bottleneck from perception toward reasoning: failures depend more on what the agent thinks than on what it sees.
- 3
- 2
- 2
- 1
- 1
- Towards Adversarial Robustness of Deep Vision Algorithms1
It is found that adversarially robust denoisers can deal with unseen types of real-world noise and the connection between adversarial robustness and generalization capability to new domains is found.
- 1
- 1
- 1
- –
- RAIN: Robust and Accurate Classification Networks with Randomization and Enhancement–
This paper proposes a novel framework to improve robustness and meanwhile retain the accuracy of given classification CNN models, termed as RAIN, which consists of two conjugate modules: structured randomization (SRd) and detail generation (DG).
- –
- Interpreting Deep Classification Models With Bayesian Inference–
A novel approach to interpret a well-trained classification model through systematically investigating effects of its hidden units on prediction making, model such a process of unit selection as an Indian Buffet Process, and derive a simplified objective function via the MAP asymptotic technique.
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.