随笔分类 - Representation Learning
摘要：目录概LinCIR代码 Gu G., Chun S., Kim W., Kang Y. and Yun S. Language-only efficient training of zero-shot composed image retrieval. CVPR, 2024. 概 本文提出了一种仅在
阅读全文
摘要：目录概Spherical Linear Interpolation (Slerp)Text-Anchored-Tuning (TAT)代码 Jiang Y. K., Huynh D., Shah A., Chen W. and Lim S. Spherical linear interpolatio
阅读全文
摘要：目录概KEDs代码 Suo Y., Ma F., Zhu L. and Yang Y. Knowledge-enhanced dual-stream zero-shot composed image retrieval. CVPR, 2024. 概 以往的 zero-shot Composed Im
阅读全文
摘要：目录概Pic2Word代码 Saito K., Sohn K., Zhang X., Li C., Lee C., Saenko K., and Pfister T. Pic2Word: Mapping pictures to words for zero-shot composed image r
阅读全文
摘要：目录概LPMM代码 Li B., Chen J. and Zhu J. Memory efficient optimizers with 4-bit states. NeurIPS, 2023. 概 本文介绍了一种支持 4-bit 的优化器量化方法. LPMM 这篇文章的工作主要继承自 [8-bit
阅读全文
摘要：目录概8-bit Optimizers Dettmers T., Lewis M., Shleifer S. and Zettlemoyer L. 8-bit optimizers via block-wise quantization. ICLR, 2022. 概 本文提出了一种 8-bit 的优
阅读全文
摘要：目录概Lion代码 Chen X., Liang C., Huang D., Real E., Wang K., Liu Y., Pham H., Dong X., Luong T., Hsieh C., Lu Y. and Le Q. V. Symbolic discovery of optimi
阅读全文
摘要：目录概主要内容代码 Wu Y., Zhang L., Mo F., Zhu T., Ma W. and Nie J. Unifying graph convolution and contrastive learning in collaborative filtering. KDD, 2024.
阅读全文
摘要：目录概主要内容原文代码 Tan Z., Zhang Y., Yang J. and Yuan Y. Contrastive learning is spectral clustering on similarity graph. ICLR, 2024. 概 本文将对比学习与谱聚类联系在一起. 主要内
阅读全文
摘要：目录概Adam-mini代码 Zhang Y., Chen C., Li Z., Ding T., Wu C., Ye Y., Luo Z. and Sun R. Adam-mini: Use fewer learning rates to gain more. arXiv preprint, 20
阅读全文
摘要：目录概符号说明GaLore Zhao J., Zhang Z., Chen B., Wang Z., Anandkumar A. and Tian Y. GaLore: Memory-efficient llm training by gradient low-rank projection. IC
阅读全文
摘要：目录概BAdam代码 Luo Q., Yu H. and Li X. BAdam: A memory efficient full parameter optimization method for large language models. arXiv preprint, 2024. 概 本文介
阅读全文
摘要：目录概符号说明所有参数的 Hessian 矩阵Block-wise Hessian代码 Zhang Y., Chen C., Ding T., Li Z., Sun R. and Luo Z. Why transformers need adam: a hessian perspective. ar
阅读全文
摘要：目录概符号说明MotivationNeo-GNN代码 Neo-GNNs: Neighborhood overlap-aware graph neural networks for link prediction. NeurIPS, 2021. 概 一种计算上相对高效的, 同时利用结构信息和特征信息的
阅读全文
摘要：目录概AdaBelief代码 Zhuang J., Tang T., Ding Y., Tatikonda S., Dvornek N., Papademetris X. and Duncan J. S. AdaBelief Optimizer: Adapting stepsizes by the
阅读全文
摘要：目录概符号说明Dirichlet energy and Gradient-flowHeat equationGradient flows on graphs: th learnable caseAttraction and repulsionLow vs high frequency dominan
阅读全文
摘要：目录概SAT代码 Chen D., O'Bray L. and Borgwardt K. Structure-aware transformer for graph representation learning. ICML, 2022. 概 Graph + Transformer + 修改 att
阅读全文
摘要：目录概LLaVA代码 Liu H., Li C., Wu Q. and Lee Y. J. Visual Instruction Tuning. NeurIPS, 2023. 概 LLaVA. LLaVA LLaVA 希望用 LLM 推理模态特征, 想法很简单: 用 Vision Encoder 得
阅读全文
摘要：目录概Mamba代码 Gu A. and Dao T. Mamba: Linear-time sequence modeling with selective state spaces. 2023. 概 Mamba. Mamba S4 和 S4D 虽然解决了 SSM 计算速度的问题, 但是有一个前提
阅读全文
摘要：目录概H3代码 Fu D. Y., Dao T., Saab K. K., Thomas A. W., Rudra A. and Re C. Hungry hungry hippos: towards language modeling with state space models. 2022.
阅读全文
