Jiangmiao Pang

30

Papers

342

Total Citations

Papers (30)

LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D Capabilities

Unified Human-Scene Interaction via Prompted Chain-of-Contacts

Aether: Geometric-Aware Unified World Modeling

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation

ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization

Dense Distinct Query for End-to-End Object Detection

Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation

Side-Aware Boundary Localization for More Precise Object Detection

Monocular 3D Object Detection with Depth from Motion

Dense Siamese Network for Dense Unsupervised Learning

Libra R-CNN: Towards Balanced Learning for Object Detection

RoboGround: Robotic Manipulation with Grounded Vision-Language Priors

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Adapting Object Detectors via Selective Cross-Domain Alignment

Hybrid Task Cascade for Instance Segmentation

Quasi-Dense Similarity Learning for Multiple Object Tracking

Seesaw Loss for Long-Tailed Instance Segmentation

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

K-Net: Towards Unified Image Segmentation

OV-PARTS: Towards Open-Vocabulary Part Segmentation