Lu Sheng

papers

2,862

total citations

papers (25)

Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues

ECCV 2020arXiv

982

citations

WorldSimBench: Towards Video Generation Models as World Simulators

ICML 2025arXiv

842

citations

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

NEURIPS 2023arXiv

207

citations

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

CVPR 2021arXiv

183

citations

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

CVPR 2021arXiv

111

citations

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception

CVPR 2024arXiv

citations

MV-Adapter: Multi-View Consistent Image Generation Made Easy

ICCV 2025arXiv

citations

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

CVPR 2024arXiv

citations

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

CVPR 2023arXiv

citations

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

CVPR 2025arXiv

citations

Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

CVPR 2025arXiv

citations

SketchSampler: Sketch-Based 3D Reconstruction via View-Dependent Depth Sampling

ECCV 2022arXiv

citations

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

CVPR 2025arXiv

citations

Improving RGB-D Point Cloud Registration by Learning Multi-Scale Local Linear Transformation

ECCV 2022arXiv

citations

Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

AAAI 2024arXiv

citations

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

NEURIPS 2025arXiv

citations

StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition

ICCV 2021

citations

3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

CVPR 2022

citations

3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

ICCV 2021

citations

Lu Sheng

papers (25)

Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues

WorldSimBench: Towards Video Generation Models as World Simulators

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception

MV-Adapter: Multi-View Consistent Image Generation Made Easy

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

SketchSampler: Sketch-Based 3D Reconstruction via View-Dependent Depth Sampling

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Improving RGB-D Point Cloud Registration by Learning Multi-Scale Local Linear Transformation

Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Powering One-shot Topological NAS with Stabilized Share-parameter Proxy

Data-Free Generalized Zero-Shot Learning

Siamese DETR

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition

3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

papers (25)

Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues

WorldSimBench: Towards Video Generation Models as World Simulators

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception

MV-Adapter: Multi-View Consistent Image Generation Made Easy

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

SketchSampler: Sketch-Based 3D Reconstruction via View-Dependent Depth Sampling

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Improving RGB-D Point Cloud Registration by Learning Multi-Scale Local Linear Transformation

Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Powering One-shot Topological NAS with Stabilized Share-parameter Proxy

Data-Free Generalized Zero-Shot Learning

Siamese DETR

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition

3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds