MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Modelsby Ziyu Liu, Yuhang Zang, Xiaoyi…
Evaluating Explanations Through LLMs: Beyond Traditional User Studiesby Francesco Bombassei De Bona, Gabriele Dominici, Tim…
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversationby Qinglin Zhang, Luyao Cheng, Chong Deng,…
Large Language Models Empowered Personalized Web Agentsby Hongru Cai, Yongqi Li, Wenjie Wang, Fengbin Zhu,…
Unsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignmentby Indrajeet Ghosh, Garvit…
Optimizing LLMs with Direct Preferences: A Data Efficiency Perspectiveby Pietro Bernardelle, Gianluca DemartiniFirst submitted to…
Learning How to Vote With Principles: Axiomatic Insights Into the Collective Decisions of Neural Networksby…
Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual…
Boosting Jailbreak Transferability for Large Language Modelsby Hanqing Liu, Lifeng Zhou, Huanqian YanFirst submitted to…
GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNetsby Oh Joon Kwon, Daiki…