Yunde Jia

21

Papers

45

Total Citations

Papers (21)

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Residual Hyperbolic Graph Convolution Networks

Consistency of Compositional Generalization Across Multiple Levels

World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving

3D Shape Reconstruction From Images in the Frequency Domain

Deep 3D Portrait From a Single Image

Learning to Optimize on SPD Manifolds

A Decomposition Model for Stereo Matching

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Global-Aware Registration of Less-Overlap RGB-D Scans

Maintaining Reasoning Consistency in Compositional Visual Question Answering

Exploring Data Geometry for Continual Learning

Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language

Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning

Curvature Generation in Curved Spaces for Few-Shot Learning

Sparse Point Guided 3D Lane Detection

Parameterized Cost Volume for Stereo Matching

Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks

Diving into the Fusion of Monocular Priors for Generalized Stereo Matching

From Notation to Gesture: Virtual Conductor Gesture Generation in VR via Structured Score Semantics

Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds