Di Wang

28

Papers

108

Total Citations

Papers (28)

Distilling Autoregressive Models to Obtain High-Performance Non-autoregressive Solvers for Vehicle Routing Problems with Faster Inference Speed

XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?

FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

Scaling Laws for Floating–Point Quantization Training

A Solvable Attention for Neural Scaling Laws

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

LAFA: Multimodal Knowledge Graph Completion with Link Aware Fusion and Aggregation

Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks

Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion

Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization

Improving Interpretation Faithfulness for Vision Transformers

A Field Guide for Pacing Budget and ROS Constraints

Understanding Forgetting in Continual Learning with Linear Regression

Semi-supervised Concept Bottleneck Models

Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling

Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction

Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models

ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters

CognitionCapturer: Decoding Visual Stimuli from Human EEG Signal with Multimodal Information

Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization

Fair Text-to-Image Diffusion via Fair Mapping

Image Content Generation with Causal Reasoning