Hybrid Preference Optimization: Augmenting Direct Preference Optimization with Auxiliary Objectivesby Anirudhan Badrinath, Prabhat Agarwal, Jiajing…
Towards Dialogues for Joint Human-AI Reasoning and Value Alignmentby Elfia Bezou-Vrakatseli, Oana Cocarascu, Sanjay ModgilFirst…
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignmentby Xin Xiao, Bohong Wu, Jiacong Wang,…
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationby Tianchen Zhao, Xuefei Ning,…
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT…
Entity Alignment with Noisy Annotations from Large Language Modelsby Shengyuan Chen, Qinggang Zhang, Junnan Dong,…
Uncertainty Management in the Construction of Knowledge Graphs: a Surveyby Lucas Jarnac, Yoan Chabot, Miguel…
Position: Foundation Agents as the Paradigm Shift for Decision Makingby Xiaoqian Liu, Xingzhou Lou, Jianbin…
Compositional Few-Shot Class-Incremental Learningby Yixiong Zou, Shanghang Zhang, Haichen Zhou, Yuhua Li, Ruixuan LiFirst submitted…
CulturePark: Boosting Cross-cultural Understanding in Large Language Modelsby Cheng Li, Damien Teney, Linyi Yang, Qingsong…