Xihui Liu

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

arXiv 2026

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

arXiv 2026

PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

arXiv 2026

MultiWorld: Scalable Multi-Agent Multi-View Video World Models

arXiv 2026

MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data

arXiv 2026

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

arXiv 2026

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?

arXiv 2026

Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction

arXiv 2026

AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation

arXiv 2026

GameFactory: Creating New Games with Generative Interactive Videos

ICCV 2025

AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation

arXiv 2025

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation

arXiv 2025

DreamCube: 3D Panorama Generation via Multi-plane Synchronization

arXiv 2025

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

arXiv 2025

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

CVPR 2025 1

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning

arXiv 2025

Personalized Text-to-Image Generation with Auto-Regressive Models

arXiv 2025

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

arXiv 2025

VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

arXiv 2025

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

arXiv 2025

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

arXiv 2025

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

arXiv 2025

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

arXiv 2025

OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

arXiv 2025

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

arXiv 2025

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

arXiv 2025

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

arXiv 2025

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

arXiv 2025

HoloPart: Generative 3D Part Amodal Segmentation

arXiv 2025

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

ICCV 2025

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

ICCV 2025

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

arXiv 2025

GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing

arXiv 2025

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

CVPR 2025 1

PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines

arXiv 2024

Parallelized Autoregressive Visual Generation

CVPR 2025 1

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

CVPR 2025 1

Editing Massive Concepts in Text-to-Image Diffusion Models

arXiv 2024

SAMPart3D: Segment Any Part in 3D Objects

arXiv 2024

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

arXiv 2024

DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion

arXiv 2024

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

ICCV 2025

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

ICCV 2025

LVD-2M: A Long-take Video Dataset with Temporally Dense Captions

arXiv 2024

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

CVPR 2025 1

BEACON: Benchmark for Comprehensive RNA Tasks and Language Models

arXiv 2024

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

arXiv 2024

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

ICCV 2025

SAM3D: Segment Anything in 3D Scenes

arXiv 2023

EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning

arXiv 2023

A Survey of Reasoning with Foundation Models

arXiv 2023

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

arXiv 2023

OV-PARTS: Towards Open-Vocabulary Part Segmentation

NeurIPS 2023 11

DDP: Diffusion Model for Dense Visual Prediction

ICCV 2023 1

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

CVPR 2024 1