Jinyi Hu

7

Papers

468

Total Citations

1

Affiliations

Affiliations

Tsinghua University

Papers (7)

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

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

NVILA: Efficient Frontier Visual Language Models

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables