Xiang Wang

21

Papers

441

Total Citations

Papers (21)

InstructVideo: Instructing Video Diffusion Models with Human Feedback

Towards 3D Molecule-Text Interpretation in Language Models

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model

Language Representations Can be What Recommenders Need: Findings and Potentials

Text-to-Image Generation for Abstract Concepts

Reinforced Lifelong Editing for Language Models

HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters

SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

DreamRelation: Relation-Centric Video Customization

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Intermediate Connectors and Geometric Priors for Language-Guided Affordance Segmentation on Unseen Object Categories

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

LASO: Language-guided Affordance Segmentation on 3D Object

Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games