Chunhua Shen

21

Papers

242

Total Citations

Papers (21)

8976 PointAttN: You Only Need Attention for Point Cloud Completion

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

Aether: Geometric-Aware Unified World Modeling

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

Revisiting Convolution Architecture in the Realm of DNA Foundation Models

SMSTracker: Tri-path Score Mask Sigma Fusion for Multi-Modal Tracking

Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection

POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction

Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning

MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data

Traffic Scene Parsing through the TSP6K Dataset

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

Floating Anchor Diffusion Model for Multi-motif Scaffolding

Generative Active Learning for Long-tailed Instance Segmentation

SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

On the Trajectory Regularity of ODE-based Diffusion Sampling

Unified Open-World Segmentation with Multi-Modal Prompts