AIPaperNotes

Record daily reading of papers and related reproduction results in Chinese.

For more notes, please follow the blog: https://nopsled.blog.csdn.net/

Paper Catalog

Embedding

• NV-EMBED [Link]

Flow

• Flow Matching [Link]

LLM

• Agent: LLM-based Single/Multi Agent model/system

  • DeepResearch:
    • WebSailor [Link]
    • WebWatcher [Link]
  • Memory:
    • Dynamic Cheatsheet
  • Reflection:
    • Metacognitive Reuse [Link]
  • Router:
    • Router-R1

• Base Model: Large Language Model

  • Zhipu AI
    • GLM 4.5 [Link]
  • OpenAI
    • gpt-oss [Link]

• Prompt: Prompt Engineering

  • Context Learning
    • ACE [Link]

• Omni: LLM-based full modal model

  • Qwen2.5 - Omni [Link]
  • M3 - Agent [Link]

• Quantization: Model Weight/Optimizer/Activation Compressing

  • COAT [Link]

• Reasoning: Long CoT model

  • Deepseek - R1 [Link]

• Speech: Speech LLM

  • ALM: Audio LLM for auido Input
    • Audio Flamingo 3 [Link]

• Survey

  • DeepRearch [Link]

• Training: LLM Model Training:

  • FIM (fill-in-the-middle)
  • Multi-token Prediction (Meta) [Link]

• VLM: Model Weight/Optimizer/Activation Compressing

  • Qwen - VL [Link]
  • LLaVA [Link]

Visual Encoder

• Language-Image Representation Learning:
  • CLIP [Link]
  • SigLIP [Link]
  • LIFT [Link]