Pheng-Ann Heng

16

Papers

143

Total Citations

Papers (16)

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

NeurIPS 2025arXiv

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

NeurIPS 2025arXiv

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models

PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion

SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation

COS3D: Collaborative Open-Vocabulary 3D Segmentation

NeurIPS 2025arXiv

ANEDL: Adaptive Negative Evidential Deep Learning for Open-Set Semi-supervised Learning

DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems

PointPatchMix: Point Cloud Mixing with Patch Scoring

EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights

Memory-Efficient Prompt Tuning for Incremental Histopathology Classification

UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation

Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting

Fast Image Super-Resolution via Consistency Rectified Flow

Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resection with Pringle Maneuver

MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding