Rui Wang

74

Papers

199

Total Citations

Papers (74)

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

AffineQuant: Affine Transformation Quantization for Large Language Models

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

Longhorn: State Space Models are Amortized Online Learners

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

F3Loc: Fusion and Filtering for Floorplan Localization

Do Large Language Models Truly Understand Geometric Structures?

DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Revisiting Change Captioning from Self-supervised Global-Part Alignment

Attention-Imperceptible Backdoor Attacks on Vision Transformers

LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data

VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things

R-DTI: Drug Target Interaction Prediction Based on Second-Order Relevance Exploration

LidarGait++: Learning Local Features and Size Awareness from LiDAR Point Clouds for 3D Gait Recognition

T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration

Frequency Shuffling and Enhancement for Open Set Recognition

SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation

Logit Standardization in Knowledge Distillation

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

SEED-Bench: Benchmarking Multimodal Large Language Models

Outlier-aware Slicing for Post-Training Quantization in Vision Transformer

FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames

Improving Open-Ended Text Generation via Adaptive Decoding

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution

SketchNet: Sketch Classification With Web Images

Binarized Mode Seeking for Scalable Visual Pattern Discovery

Image Deblurring via Extreme Channels Prior

Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines

Learning Generative Models of Shape Handles

DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data

SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition

BEVT: BERT Pretraining of Video Transformers

Delving Into Shape-Aware Zero-Shot Semantic Segmentation

PACO: Parts and Attributes of Common Objects

Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

LidarGait: Benchmarking 3D Gait Recognition With Point Clouds

Stereo DSO: Large-Scale Direct Sparse Visual Odometry With Stereo Cameras

Shape Reconstruction Using Differentiable Projections and Deep Priors

PreDet: Large-Scale Weakly Supervised Pre-Training for Detection

The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Pluralistic Aging Diffusion Autoencoder

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

CASSPR: Cross Attention Single Scan Place Recognition

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection

Plug-and-Play PPO: An Adaptive Point Prompt Optimizer Making SAM Greater

Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry

SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures

GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule

A3GS: Arbitrary Artistic Style into Arbitrary 3D Gaussian Splatting

Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

IntrinsicControlNet: Cross-distribution Image Generation with Real and Unreal

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards

Semi-Supervised Neural Architecture Search

Universal Graph Convolutional Networks

Curriculum Disentangled Recommendation with Noisy Multi-feedback

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

Few-Shot Fast-Adaptive Anomaly Detection

Meta-Learning Dynamics Forecasting Using Task Inference

A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification