Tsung-Han Wu

8

Papers

109

Total Citations

Papers (8)

Self-correcting LLM-controlled Diffusion Models

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

NeurIPS 2025arXiv

LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery

MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer

ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation

D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation

See Say and Segment: Teaching LMMs to Overcome False Premises

S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation