Yuan Yao

19

Papers

641

Total Citations

Papers (19)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data

Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning

Towards Fine-grained Interactive Segmentation in Images and Videos

NExT-Chat: An LMM for Chat, Detection and Segmentation

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior

LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians

UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images

Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks

3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling