paper reading

发表于 更新于 分类于

把看过的论文做一个总结，防止我忘掉 # 阅读习惯 1. 看到公式变量用绿色标注一下！不用这样…… 2. 几遍 1. 全文通读，分清楚每句话的意义，只记录重要的话，写下问题 2. 每章提炼出重点 3. 回答以上问题

paper集合

  1. FULL PARAMETER FINE-TUNING FOR LARGE LANGUAGE MODELS WITH LIMITED RESOURCES
    1. 全参数|微调
  2. Towards A Unified View Of Parameter-Efficient Transfer Learning
    1. 微调|高效参数
  3. TinyLLM: Learning a Small Student from Multiple Large Language Models
  4. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  5. FlexGen: high-throughput generative inference of large language models
  6. LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model
    1. Fine-Tuning
  7. TRANSFORMER EXPLAINER: Interactive Learning of Text-Generative Models
    1. 没啥营养，把transformer的过程搞了个可视化（也没啥用），唯一的贡献就是让我重新梳理了一遍transformer
  8. CLLMs: Consistency Large Language Models
  9. AN EMULATOR FOR FINE-TUNING LARGE LANGUAGE MODELS USING SMALL LANGUAGE MODELS
  10. Kubric: A scalable dataset generator
  11. GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
  12. 毫无印象的论文
  13. MANISKILL3: GPU PARALLELIZED ROBOTICS SIMULATION AND RENDERING FOR GENERALIZABLE EMBODIED AI
  14. Aligner: Efficient Alignment by Learning to Correct
  15. A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More
  16. 综述文章，对齐
  17. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
    1. 对robotic在强化学习上的总结
  18. Generative Artificial Intelligence in Robotic Manipulation: A Survey
  19. ai in 机器人操作的综述，全讲的方法
  20. VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
  21. 从视频中获得知识，没看仔细
  22. CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
  23. 这个数据收集方式有点野了
  24. DIFFTACTILE: A PHYSICS-BASED DIFFERENTIABLE TACTILE SIMULATOR FOR CONTACT-RICH ROBOTIC MANIPULATION
    1. 借助tactile实现精细操作，但是只有2指
    2. 但是还有一点问题，以后脑子清晰点再看看