Dan Xu

Assistant Professor@CSE, HKUST·中国香港·OpenReview

研究方向

Deep Learning · Scene Understanding · Structured Representation Learning · Depth estimation · Multi-task learning · NeRF scene representation learning · multi-modal learning

Dan Xu

FullPart: Generating each 3D Part at Full Resolution

Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos

Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction

Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding

UniGP: Taming Diffusion Transformer for Prior Preserved Unified Generation and Perception

Attribute-Relation Guided Compositional Alignment for Weakly Supervised Referring Expression Comprehension

CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving

Learning Explicit Semantic-Spatial Synergy for Weakly Supervised Referring Image Segmentation

ExGS: Extreme 3D Gaussian Compression with Diffusion Priors

Proxy-GS: Efficient 3D Gaussian Splatting via Proxy Mesh

HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

3DGS-Det: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection

Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation

X-VILA: Cross-Modality Alignment for Large Language Models

Sample-efficient Imitative Multi-token Decision Transformer for Real-world Driving