Ning Yu

21

Papers

443

Total Citations

Papers (21)

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

HIVE: Harnessing Human Feedback for Instructional Visual Editing

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset

Reference-Based 3D-Aware Image Editing with Triplanes

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution

Detecting Adversarial Data Using Perturbation Forgery

Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints

Dual Contrastive Loss and Attention for GANs

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

RepMix: Representation Mixing for Robust Attribution of Synthesized Images

Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture

Text2Data: Low-Resource Data Generation with Textual Control

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

Mask-Free OVIS: Open-Vocabulary Instance Segmentation Without Manual Mask Annotations

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild