Summary of Sftmix: Elevating Language Model Instruction Tuning with Mixup Recipe, by Yuxin Xiao et al.
SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipeby Yuxin Xiao, Shujian Zhang, Wenxuan Zhou,…
Summary of Differential Transformer, by Tianzhu Ye et al.
Differential Transformerby Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, Furu…
Summary of Dept: Decoupled Embeddings For Pre-training Language Models, by Alex Iacob et al.
DEPT: Decoupled Embeddings for Pre-training Language Modelsby Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, William F.…
Summary of Tidaldecode: Fast and Accurate Llm Decoding with Position Persistent Sparse Attention, by Lijie Yang et al.
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attentionby Lijie Yang, Zhihao Zhang,…
Summary of Sparsepo: Controlling Preference Alignment Of Llms Via Sparse Token Masks, by Fenia Christopoulou et al.
SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masksby Fenia Christopoulou, Ronald Cardenas, Gerasimos…
Summary of Timer-xl: Long-context Transformers For Unified Time Series Forecasting, by Yong Liu et al.
Timer-XL: Long-Context Transformers for Unified Time Series Forecastingby Yong Liu, Guo Qin, Xiangdong Huang, Jianmin…
Summary of Tablerag: Million-token Table Understanding with Language Models, by Si-an Chen et al.
TableRAG: Million-Token Table Understanding with Language Modelsby Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos, Zifeng…
Summary of Tldr: Token-level Detective Reward Model For Large Vision Language Models, by Deqing Fu et al.
TLDR: Token-Level Detective Reward Model for Large Vision Language Modelsby Deqing Fu, Tong Xiao, Rui…
Summary of Hyperbolic Fine-tuning For Large Language Models, by Menglin Yang et al.
Hyperbolic Fine-tuning for Large Language Modelsby Menglin Yang, Aosong Feng, Bo Xiong, Jihong Liu, Irwin…
Summary of Detecting Machine-generated Long-form Content with Latent-space Variables, by Yufei Tian et al.
Detecting Machine-Generated Long-Form Content with Latent-Space Variablesby Yufei Tian, Zeyu Pan, Nanyun PengFirst submitted to…