Weili Nie

Latest

• Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
• Mode Seeking meets Mean Seeking for Long Video Generation
• Transition Matching Distillation for Fast Video Generation
• Exploring Synthesizable Chemical Space with Iterative Pathway Refinements
• GenMol: A Drug Discovery Generalist with Discrete Diffusion
• BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
• Energy-based Diffusion Language Models for Text Generation
• T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
• Truncated Consistency Models
• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
• BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs
• DiffUHaul: A Training-Free Method for Object Dragging in Images
• Molecule Generation with Fragment Retrieval Augmentation
• Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
• Compositional Text-to-Image Generation with Dense Blob Representations
• Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
• Fast Training of Diffusion Models with Masked Transformers
• Fast Sampling of Diffusion Models via Operator Learning
• I^2SB: Image-to-Image Schrödinger Bridge
• Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
• Test-time prompt tuning for zero-shot generalization in vision-language models
• Diffusion Models for Adversarial Purification
• Controllable and Compositional Generation with Latent-Space Energy-Based Models