Xihui Liu
~Xihui_Liu1
20
论文总数
10.0
年均投稿
平均评分
接收情况12/20
会议分布
ICLR
10
NeurIPS
8
ICML
2
发表论文 (20 篇)
202512 篇
4
Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
NeurIPS 2025Poster
5
Benchmarking Ethics in Text-to-Image Models: A Holistic Dataset and Evaluator for Fairness, Toxicity, and Privacy
ICLR 2025withdrawn
4
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
NeurIPS 2025Poster
4
WorldSimBench: Towards Video Generation Models as World Simulators
ICLR 2025Rejected
4
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
ICLR 2025withdrawn
3
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
ICLR 2025Poster
4
WorldSimBench: Towards Video Generation Models as World Simulators
ICML 2025Poster
4
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
NeurIPS 2025Poster
4
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
ICML 2025Poster
4
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
ICLR 2025withdrawn
4
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
NeurIPS 2025Poster
3
GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing
NeurIPS 2025Poster
20248 篇
4
TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale
ICLR 2024Rejected
4
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
NeurIPS 2024Poster
4
Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection
ICLR 2024Rejected
3
GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
NeurIPS 2024Spotlight
4
Understanding Masked Autoencoders From a Local Contrastive Perspective
ICLR 2024withdrawn
4
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
NeurIPS 2024Spotlight
4
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
ICLR 2024Poster
4
Convolution on Your 12× Wide Feature: A ConvNet with Nested Design
ICLR 2024withdrawn