G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Modelsby Pengyue Jia,…
Exploring Alignment in Shared Cross-lingual Spacesby Basel Mousi, Nadir Durrani, Fahim Dalvi, Majd Hawasly, Ahmed…
ALI-Agent: Assessing LLMs’ Alignment with Human Values via Agent-based Evaluationby Jingnan Zheng, Han Wang, An…
Let’s Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text…
Instruction Tuning With Loss Over Instructionsby Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison,…
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignmentby Wei Li, Hehe Fan,…
AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capabilityby Fei Zhao, Taotian Pang, Chunhui Li,…
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reductionby Tingchen Fu, Deng Cai,…
Assessing Political Bias in Large Language Modelsby Luca Rettenberger, Markus Reischl, Mark SchuteraFirst submitted to…
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Processby Ermo Hua, Biqing Qi, Kaiyan Zhang,…