Picture for Dongyan Zhao

Dongyan Zhao

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment

Add code
Sep 02, 2024
Viaarxiv icon

ReMamba: Equip Mamba with Effective Long-Sequence Modeling

Add code
Sep 01, 2024
Viaarxiv icon

Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering

Add code
Aug 27, 2024
Viaarxiv icon

In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting

Add code
Aug 23, 2024
Viaarxiv icon

Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering

Add code
Aug 23, 2024
Viaarxiv icon

End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling

Add code
Jul 23, 2024
Viaarxiv icon

Graph-Structured Speculative Decoding

Add code
Jul 23, 2024
Viaarxiv icon

Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules

Add code
Jul 09, 2024
Viaarxiv icon

Unlocking the Potential of Model Merging for Low-Resource Languages

Add code
Jul 04, 2024
Viaarxiv icon

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models

Add code
Jun 24, 2024
Viaarxiv icon