Fei Huang

24

Papers

1,118

Total Citations

Papers (24)

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Preference Ranking Optimization for Human Alignment

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

Platypus: A Generalized Specialist Model for Reading Text in Various Forms

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.

Training-Free Long-Context Scaling of Large Language Models

EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce

SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding

OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Unsupervised Multi-Modal Neural Machine Translation

HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training

Learning Trajectory-Word Alignments for Video-Language Tasks

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

RRHF: Rank Responses to Align Language Models with Human Feedback

Debiased and Denoised Entity Recognition from Distant Supervision

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs