Kylin Page

A fool who dreams.

2024年2月多模态大模型幻觉综述

A Survey on Hallucination in Large Vision Language Models

[TOC] Abstract “hallucination”：the misalignment between factual visual content and corresponding textual generation Intro 视觉幻觉按三元分类（ternary taxonomy）： hallucination on object, attribute...

Posted by Kylin on April 18, 2024

幻方2025届算法面筋

Interview to DeepSeek

[TOC] 一面 实习经历深挖 lora初始化方法 kv cache计算方法 bs*layer*sequence*hidden_dim*parameter_size*2 vllm可以做重参数化吗？ 预训练权重在vllm框架下使用需要做哪些事情？ 手撕：layernorm怎么写？ def layernorm(hidden_states,belta,gamma): b...

Posted by Kylin on April 17, 2024

DeepSeekVL Paper Reading

Introduction to DeepSeekVL

[TOC] Abstract Architecture 线性层进行多模态对齐 Reference

Posted by Kylin on April 16, 2024

DeepSeekLLM Paper Reading

Introduction to DeepSeekLLM

[TOC] Abstract Architecture The micro design of DeepSeek LLM largely follows the design of LLaMA (Touvron et al., 2023a,b), adopting a Pre-Norm structure with RMSNorm (Zhang and Sennrich, 2019) ...

Posted by Kylin on April 16, 2024

记忆增强的视频理解 MALLM paper reading

Memory Augmented Large Multimodal Model for LongTerm Video Understanding

[TOC] CVPR 2024 Abstract 以前MLLM的问题：can only take in a limited number of frames for short video understanding motivation：Instead of trying to process more frames simultaneously like most exi...

Posted by Kylin on April 16, 2024

Claude 3 Technical Report

The Claude 3 Model Family

[TOC] Abstract 三个模型定位，由强到弱： Claude 3 Opus, our most capable offering Claude 3 Sonnet, which provides a combination of skills and speed Claude 3 Haiku, our fastest and least expensive model...

Posted by Kylin on April 16, 2024

Infini Attention 详解及数学推导

Efficient Infinite Context Transformers with Infini Attention 详解

[TOC] Abstract 达到的效果：bounded memory and computation 方法的本质：new attention technique dubbed Infini-attention, 即修改的attention机制 Intro 宏观的想法上就是Q分别在 previous segments 和 local segmenet上分别做attention，只对...

Posted by Kylin on April 14, 2024

Mini Gemini

Mining the Potential of Multimodality Vision Language Models

[TOC] Abstract 这个模型是any-to-any的 we propose to utilize an additional visual encoder for high-resolution refinement without increasing the visual token count. Intro 输入端： 模型视觉输入端是dual-encode...

Posted by Kylin on April 13, 2024

幻方2025届大模型算法笔试

coding to HF

[TOC] 选择题 填空题 OJ

Posted by Kylin on April 11, 2024

Stable Diffusion浅析&性能优化研究

interview to SD&SDSystem

[TOC] Intro To SD 参考1 Opt in SD 参考2 Reference 浅谈Stable Diffusion. https://zhuanlan.zhihu.com/p/637758440 ↩ 扩散模型(Diffusion Model)首篇综述-Diffusion Mod...

Posted by Kylin on April 8, 2024

FEATURED TAGS
From Bohemia Linux Git Cloud Computer Architecture Database machine learning paper software coding quant Object Detection job programming Competition lecture nlp competition
ABOUT ME

Master degree candidate in THU, interested in mobile computing and wireless sensors.

✉️ qilin_chan@icloud.com

FRIENDS