Tao Xiang
- Papers
- 25
Cite
Notes
Only stored in your browser.
Authored papers
25Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
arXiv 2026
VecGlypher: Unified Vector Glyph Generation with Language Models
arXiv 2026
Scaling Zero-Shot Reference-to-Video Generation
arXiv 2025
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
arXiv 2025
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
arXiv 2025
Chirpy3D: Creative Fine-grained 3D Object Fabrication via Part Sampling
arXiv 2025
Learning Flow Fields in Attention for Controllable Person Image Generation
CVPR 2025 1
Faster Diffusion via Temporal Attention Decomposition
arXiv 2024
Do Generalised Classifiers really work on Human Drawn Sketches?
arXiv 2024
PartCraft: Crafting Creative Objects by Parts
arXiv 2024
SketchINR: A First Look into Sketches as Implicit Neural Representations
CVPR 2024 1
DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination
arXiv 2023
Wired Perspectives: Multi-View Wire Art Embraces Generative AI
CVPR 2024 1
FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
CVPR 2023 1
Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes
CVPR 2024 1
DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion
ICCV 2023 1
3D VR Sketch Guided 3D Shape Prototyping and Exploration
ICCV 2023 1
SketchXAI: A First Look at Explainability for Human Sketches
CVPR 2023 1
SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation
arXiv 2023
Unsupervised Hashing with Similarity Distribution Calibration
arXiv 2023
Softmax-free Linear Transformers
arXiv 2022
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
NeurIPS 2021 12
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
CVPR 2021 1
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
arXiv 2019
Learning a Deep Embedding Model for Zero-Shot Learning
learning-a-deep-embedding-model-for-zero-shot-1
Affiliations
Frequent co-authors
10from 25 papers