Jingdong Wang

Deforming Videos to Masks: Flow Matching for Referring Video Segmentation

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding

Representation Alignment for Diffusion Transformers without External Components

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

GeoLoom: High-quality Geometric Diagram Generation from Textual Input

Pyramid Patchification Flow for Visual Generation

Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation

Stochastic Gaussian Zeroth-Order Optimization: Improved Convergence Analysis under Skewed Hessian Spectra

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling

Unified Multimodal Model as Auto-Encoder

MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation

Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling

MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

Improving Multi-modal Large Language Model through Boosting Vision Capabilities

GAP: Scalable Driving with Generative Aided Planner

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap prior

Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?

Unveiling the Secret of AdaLN-Zero in Diffusion Transformer

UMVMap: Improving Vectorized Map Construction via Multi-vehicle Perspectives

DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making

The Advancement in Stochastic Zeroth-Order Optimization: Mechanism of Accelerated Convergence of Gaussian Direction on Objectives with Skewed Hessian Eigenvalues