Ning Yu

10

Papers

443

Total Citations

Papers (10)

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

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

Text2Data: Low-Resource Data Generation with Textual Control

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content