Summary of Rainbowpo: a Unified Framework For Combining Improvements in Preference Optimization, by Hanyang Zhao et al.
RainbowPO: A Unified Framework for Combining Improvements in Preference Optimizationby Hanyang Zhao, Genta Indra Winata,…
RainbowPO: A Unified Framework for Combining Improvements in Preference Optimizationby Hanyang Zhao, Genta Indra Winata,…
Improving Portfolio Optimization Results with Bandit Networksby Gustavo de Freitas Fonseca, Lucas Coelho e Silva,…
Mechanistic Behavior Editing of Language Modelsby Joykirat Singh, Subhabrata Dutta, Tanmoy ChakrabortyFirst submitted to arxiv…
LoRTA: Low Rank Tensor Adaptation of Large Language Modelsby Ignacio Hounie, Charilaos Kanatsoulis, Arnuv Tandon,…
Complex-valued convolutional neural network classification of hand gesture from radar imagesby Shokooh KhandanFirst submitted to…
FactAlign: Long-form Factuality Alignment of Large Language Modelsby Chao-Wei Huang, Yun-Nung ChenFirst submitted to arxiv…
CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMsby Kangsheng…
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generationby Liang Chen,…
Improving Fuzzy Rule Classifier with Brain Storm Optimization and Rule Modificationby Yan Huang, Wei Liu,…
Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimationby Shuting Zhao, Chenkang Du, Kristin…