Ziyu Guo
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20GENIUS: Generative Fluid Intelligence Evaluation Suite
arXiv 2026
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
arXiv 2025
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
arXiv 2025
CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
arXiv 2025
Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
arXiv 2025
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
arXiv 2025
DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
arXiv 2025
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
arXiv 2025
Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
arXiv 2025
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
arXiv 2025
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
arXiv 2025
IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
arXiv 2025
SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
arXiv 2024
SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
arXiv 2024
MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
arXiv 2024
ImageBind-LLM: Multi-modality Instruction Tuning
arXiv 2023
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
arXiv 2023
Personalize Segment Anything Model with One Shot
arXiv 2023
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
ICCV 2023 1
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
ICCV 2023 1
Affiliations
Frequent co-authors
10from 20 papers