论文阅读:Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems
论文阅读:DQ-LoRe:Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
论文阅读:Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
论文阅读:Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
PyramidKV
论文阅读:RCoT Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought
AI 情感聊天机器人工作之旅 —— 与复读机问题的相遇与别离
论文阅读:Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning 数据子集挑选方法
论文阅读:The Unreasonable Ineffectiveness of the Deeper Layers 层剪枝与模型嫁接的“双生花”
论文阅读:RHO-1:Not All Tokens Are What You Need 选择你需要的 Tokens 参与训练
论文阅读:《Sequence can Secretly Tell You What to Discard》,减少推理阶段的 kv cache
论文阅读:Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
avatar
clvsit
人生不是戏剧,而我亦非主角
Follow Me
公告
知乎和 CSDN 同名 clvsit,目前在将本地的笔记逐步迁移到这,所以会看到过去日期的文章不断增多