Profiles2023-2026ORCID 0000-0002-3802-4644
Shengfeng He
Singapore Management University
26Papers
22Last author
32Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers26
- FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured SpeculationAuthor 9 of 9CVPR 2026 · 2 citations
- Self-Corrected Image Generation with Explainable Latent RewardsAuthor 5 of 5CVPR 2026 · 1 citation
- Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph ModelAuthor 4 of 4ICLR 2026
- ME: Continual Vision-and-Language Navigation via Mixture of Macro and Micro ExpertsAuthor 4 of 4ICLR 2026
- Modeling the Visual Ambiguity of Human SketchesAuthor 9 of 9CVPR 2026
- Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly DetectionAuthor 7 of 7NeurIPS 2025 · 8 citations
- Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object DetectionAuthor 2 of 8NeurIPS 2025 · 7 citations
- StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion ModelsAuthor 8 of 8NeurIPS 2025 · 5 citations
- Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch GenerationAuthor 5 of 5ICCV 2025 · 2 citations
- Action Dubber: Timing Audible Actions via Inflectional FlowAuthor 5 of 5ICML 2025
- Instance-Level Video Depth in Groups Beyond OcclusionsAuthor 6 of 6ICCV 2025
- Instruct2See: Learning to Remove Any Obstructions Across DistributionsAuthor 4 of 4ICML 2025
- Knowledge Bridger: Towards Training-Free Missing Modality CompletionAuthor 2 of 8CVPR 2025
- MODfinity: Unsupervised Domain Adaptation with Multimodal Information Flow IntertwiningAuthor 6 of 6CVPR 2025
- PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem EquilibriumAuthor 3 of 7AAAI 2025
- RecDreamer: Consistent Text-to-3D Generation via Uniform Score DistillationAuthor 6 of 6ICLR 2025
- Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic PropagationAuthor 5 of 5CVPR 2024 · 12 citations
- Learning with Unreliability: Fast Few-Shot Voxel Radiance Fields with Relative Geometric ConsistencyAuthor 5 of 5CVPR 2024 · 7 citations
- DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd CountingAuthor 6 of 6ACM MM 2023 · 27 citations
- Disentangling Multi-view Representations Beyond Inductive BiasAuthor 4 of 4ACM MM 2023 · 15 citations
- CIRI: Curricular Inactivation for Residue-aware One-shot Video InpaintingAuthor 5 of 8ICCV 2023 · 12 citations
- Diffuse3D: Wide-Angle 3D Photography via Bilateral DiffusionAuthor 7 of 7ICCV 2023 · 10 citations
- Layout Generation as Intermediate Action Sequence PredictionAuthor 4 of 4AAAI 2023 · 2 citations
- NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic VideosAuthor 7 of 7ACM MM 2023 · 2 citations
- Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image RetrievalAuthor 5 of 5CVPR 2023
- Where is My Spot? Few-shot Image Generation via Latent Subspace OptimizationAuthor 5 of 5CVPR 2023
