🏢 Shanghai Jiao Tong University

Dual-Diffusion boosts binocular 3D human pose estimation accuracy by simultaneously denoising 2D and 3D pose uncertainties using a diffusion model.

DomainGallery: Few-shot domain-driven image generation via attribute-centric finetuning, solving key issues of previous works by introducing attribute erasure, disentanglement, regularization, and enh…

Diffusion-DICE: A novel offline RL method using in-sample diffusion guidance for optimal policy transformation, achieving state-of-the-art performance.

CoVoMix: Generating human-like, multi-speaker conversations with zero-shot speech synthesis.

Data connectivity profoundly shapes implicit regularization in matrix factorization for matrix completion, transitioning from low nuclear norm to low rank solutions as data shifts from disconnected to…

CondTSF: One-line plugin for time series forecasting dataset condensation, boosting performance at low condensation ratios.

Cluster-wise Graph Transformer (Cluster-GT) improves graph learning by using a novel Node-to-Cluster Attention mechanism that leverages multiple kernel learning to capture node and cluster-level infor…

LLMs’ reasoning can be improved by using internal consistency to calibrate their outputs.

AnyFit: Controllable virtual try-on for any attire combination across any scenario, exceeding existing methods in accuracy and scalability.

Siamese Transformer with Hierarchical Refinement achieves state-of-the-art lane detection accuracy by integrating global and local features and a novel Curve-IoU loss.

2DQuant achieves highly efficient and accurate low-bit image super-resolution by using a dual-stage post-training quantization method that minimizes accuracy loss in transformer-based models, surpassi…