Profiles2021-2026ORCID 0000-0002-4220-5958
Ziwei Liu
Nanyang Technological University
69Papers
32Last author
138Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers69
- The Quest for Generalizable Motion Generation: Data, Model, and EvaluationAuthor 13 of 13ICLR 2026 · 23 citations
- Video-MMMU: Evaluating Knowledge Acquisition from Multidisciplinary Professional VideosAuthor 8 of 8ACL 2026 · 1 citation
- HiStream: Efficient High-Resolution Video Generation via Redundancy Eliminated StreamingAuthor 12 of 13CVPR Findings 2026
- PhysX-3D: Physical-Grounded 3D Asset GenerationAuthor 4 of 5NeurIPS 2025 · 46 citations
- Vistadream: Sampling Multiview Consistent Images for Single-View Scene ReconstructionAuthor 3 of 6ICCV 2025 · 8 citations
- GenDoP: Auto-regressive Camera Trajectory Generation as a Director of PhotographyAuthor 4 of 6ICCV 2025 · 4 citations
- MMInA: Benchmarking Multihop Multimodal Internet AgentsAuthor 4 of 4ACL Findings 2025 · 4 citations
- Rethinking Cross-Modal Interaction in Multimodal Diffusion TransformersAuthor 6 of 8ICCV 2025 · 3 citations
- Dual-Expert Consistency Model for Efficient and High-Quality Video GenerationAuthor 7 of 7ICCV 2025 · 1 citation
- Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMMAuthor 3 of 3ICML 2025
- FreeU: Free Lunch in Diffusion U-NetAuthor 4 of 4CVPR 2024 · 111 citations
- AID: Attention Interpolation of Text-to-Image DiffusionAuthor 3 of 4NeurIPS 2024 · 30 citations
- Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic MaterialsAuthor 5 of 7NeurIPS 2024 · 21 citations
- Fresco: Spatial-Temporal Correspondence for Zero-Shot Video TranslationAuthor 3 of 5CVPR 2024 · 17 citations
- MMHead: Towards Fine-grained Multi-modal 3D Facial AnimationAuthor 5 of 6ACM MM 2024 · 17 citations
- Link-Context Learning for Multimodal LLMsAuthor 4 of 4CVPR 2024 · 7 citations
- Move Anything with Layered Scene DiffusionAuthor 4 of 7CVPR 2024 · 7 citations
- ThemeStation: Generating Theme-Aware 3D Assets from Few ExemplarsAuthor 4 of 5SIGGRAPH 2024 · 7 citations
- SparseNeRF: Distilling Depth Ranking for Few-shot Novel View SynthesisAuthor 4 of 5ICCV 2023 · 309 citations
- ReMoDiffuse: Retrieval-Augmented Motion Diffusion ModelAuthor 8 of 8ICCV 2023 · 301 citations
- What Makes Good Examples for Visual In-Context Learning?Author 3 of 3NeurIPS 2023 · 219 citations
- Rethinking Range View Representation for LiDAR SegmentationAuthor 9 of 9ICCV 2023 · 193 citations
- Segment Any Point Cloud Sequences by Distilling Vision Foundation ModelsAuthor 8 of 8NeurIPS 2023 · 169 citations
- Robo3D: Towards Robust and Reliable 3D Perception against CorruptionsAuthor 9 of 9ICCV 2023 · 151 citations
- Large Language Models are Visual Reasoning CoordinatorsAuthor 8 of 8NeurIPS 2023 · 108 citations
- PrimDiffusion: Volumetric Primitives Diffusion for 3D Human GenerationAuthor 6 of 6NeurIPS 2023 · 44 citations
- EVA3D: Compositional 3D Human Generation from 2D Image CollectionsAuthor 5 of 5ICLR 2023 · 35 citations
- 4D Panoptic Scene Graph GenerationAuthor 9 of 9NeurIPS 2023 · 33 citations
- StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned FacesAuthor 3 of 4ICCV 2023 · 33 citations
- Voxurf: Voxel-based Efficient and Accurate Neural Surface ReconstructionAuthor 6 of 7ICLR 2023 · 31 citations
Showing the 30 most recent indexed papers.
