Publications

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration

Customized Multimodal LLMs as Reward Models for Text-to-Image Generation

Towards Visual Text Grounding of Multimodal Large Language Model

A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation

SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner

TRINS: Towards Multimodal Language Models that Can Read

Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation

LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models

Customization Assistant for Text-to-Image Generation

ADoPD: A Large-Scale Document Page Decomposition Dataset

AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models

TextLap: Customizing Language Models for Text-to-Layout Planning

Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances

Towards building the federatedGPT: Federated instruction tuning

Improve Temporal Awareness of LLMs for Sequential Recommendation

ARTIST: Improving Generation of Text-rich Image by Disentanglement

LLaVAR: Enhanced Visual Instruction Tuning for Text-rich Image Understanding

Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels

VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding