Wentong Li

15

Papers

224

Total Citations

Papers (15)

Osprey: Pixel Understanding with Visual Instruction Tuning

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Scalable Autoregressive Monocular Depth Estimation

Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction

Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport

Box-Supervised Instance Segmentation with Level Set Evolution

Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation

OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM

Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering

MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction

Oriented RepPoints for Aerial Object Detection

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

Label-efficient Segmentation via Affinity Propagation