Zuyan Liu
8 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20)
👥
Mega-Team · Squad
❓
The Questioner
Top co-authors
Research topics
Keywords
multimodal large language model
(3)
visual reasoning
(2)
diffusion model
(2)
image generation
(2)
latent space
(1)
depth estimation
(1)
multimodal learning
(1)
image understanding
(1)
direct preference optimization
(1)
pre-trained model
(1)
visual concept
(1)
text-to-image model
(1)
vision-language pre-training
(1)
evaluation benchmark
(1)
latent diffusion
(1)
visual perception
(1)
attention head
(1)
inference acceleration
(1)
vision transformer
(1)
semantic segmentation
(1)
Papers
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
CVPR 2026
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
CVPR 2025
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
ICLR 2025
SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
ICCV 2025
Efficient Inference of Vision Instruction-Following Models with Elastic Cache
ECCV 2024
DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion
CVPR 2023
Unleashing Text-to-Image Diffusion Models for Visual Perception
ICCV 2023
PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers
ICCV 2021