Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks68 from public data
- Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans440
An Self-Trans approach is proposed, which synergistically integrates contrastive self-supervised learning with transfer learning to learn powerful and unbiased feature representations for reducing the risk of overfitting in COVID-19.
- OminiControl: Minimal and Universal Control for Diffusion Transformer386
OminiControl, a novel approach that rethinks how image conditions are integrated into Diffusion Transformer (DiT) architectures, demonstrates that effective image control can be achieved without architectural complexity, opening new possibilities for efficient and versatile image generation systems.
- Dataset Distillation via Factorization190
A novel approach todataset factorization is introduced, termed HaBa, which is a plug-and-play strategy portable to any existing DD baseline and can yield significant improvement on downstream classification tasks compared with previous state of the arts.
- Diffusion Probabilistic Model Made Slim167
A customized design for slim DPM is introduced, which is term as Spectral Diffusion (SD), for light-weight image synthesis, and achieves 8–18 × computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks while retaining competitive image fidelity.
- Deep Model Reassembly162
It is demonstrated that on ImageNet, the best reassemble model achieves 78.6% top-1 accuracy without fine-tuning, which could be further elevated to 83.2% with end-to-end training.
- Kolmogorov-Arnold Transformer156
The Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model, is introduced.
- Diffusion Model as Representation Learner127
An in-depth investigation of the representation power of DPMs is conducted, and a novel knowledge transfer method that leverages the knowledge acquired by generative DPMs for recognition tasks is proposed, named RepFusion.
- Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection123
A adaptive anchor assignment (ASA) substitutes the static IoU-based strategy, which enables the student network to be resistant to noisy pseudo-bounding boxes, and a Gaussian Mixture Model dynamically revises the score threshold of pseudo-bboxes, which stabilizes the number of ground truths at an early stage.
- Anything-3D: Towards Single-view Anything Reconstruction in the Wild113
Anything-3D is introduced, a methodical framework that ingeniously combines a series of visual-language models and the Segment-Anything object segmentation model to elevate objects to 3D, yielding a reliable and versatile system for single-view conditioned 3D reconstruction task.
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly103
A novel framework called pFedHR is proposed, which leverages heterogeneous model reassembly to achieve personalized federated learning and effectively reduces the adverse impact of using different public data and dynamically generates diverse personalized models in an automated manner.
- Stretchable and Self-Adhesive PEDOT:PSS Blend with High Sweat Tolerance as Conformal Biopotential Dry Electrodes97
This is the first time to demonstrate dry epidermal electrodes self-adhesive to wet skin for accurate biopotential detection and exhibit a lower contact impedance to skin than commercial Ag/AgCl gel electrodes on both dry and sweat skins.
- FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally83
The core insight of the method is that, with a reconstructed 3D-GS scene, the rendering of the 2D masks is essentially a linear function with respect to the labels of each Gaussian, and the optimal label assignment can be solved via linear programming in closed form.
- 83
- SG-Former: Self-guided Transformer with Evolving Token Reallocation78
A novel model, termed as Self-guided Transformer (SG-Former), towards effective global self-attention with adaptive fine granularity, which assigns more tokens to the salient regions for achieving fine-grained attention, while allocating fewer tokens to the minor regions in exchange for efficiency and global receptive fields.
- DSRNA: Differentiable Search of Robust Neural Architectures62
Different from previous approaches which aim to improve architectures’ robustness in an implicit way: performing adversarial training and injecting random noise, these methods explicitly and directly maximize robustness metrics to harvest robust architectures.
- Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation57
This work proposes MedWriter, a novel hierarchical retrieval mechanism to automatically extract both report and sentence-level templates for clinically accurate report generation that verified the effectiveness of the model by automatic evaluation and human evaluation on two datasets, i.e., Open-I and MIMIC-CXR.
- 52
- Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms48
A comprehensive comparative study is performed between SSL and TL regarding which one works better under different properties of data and tasks, including domain difference between source and target tasks, the amount of pretraining data, class imbalance in source data, and usage of target data for additional pretraining, etc.
- Single View Metrology in the Wild44
This work presents a novel approach to single view metrology that can recover the absolute scale of a scene represented by 3D heights of objects or camera height above the ground as well as camera parameters of orientation and field of view, using just a monocular image acquired in unconstrained condition.
- 39
- Distribution Shift Inversion for Out-of-Distribution Prediction34
This paper proposes a portable Distribution Shift Inversion (DSI) algorithm, in which, before being fed into the prediction model, the OoD testing samples are first linearly combined with additional Gaussian noise and then transferred back towards the training distribution using a diffusion model trained only on the source distribution.
- On the Generation of Medical Dialogues for COVID-1932
This work collects two dialogue datasets - CovidDialog - (in English and Chinese respectively) containing conversations between doctors and patients about COVID-19 and trains several dialogue generation models based on Transformer, GPT, and BERT-GPT to develop a medical dialogue system that can provide COVID19-related consultations.
- Mixture of Experts Made Intrinsically Interpretable30
MoE-X, a Mixture-of-Experts (MoE) language model designed to be interpretable, achieves performance comparable to dense models while significantly improving interpretability, with interpretability surpassing even sparse autoencoder (SAE)-based approaches.
- 29
- 29
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.