raymin0223/mixture_of_recursions

• highreadme#1

  Add an explicit introductory sentence to the README to clarify the repo's purpose.

  原因：

  复制粘贴的修复

  复制

  This repository provides the official PyTorch implementation of the Mixture-of-Recursions (MoR) model, as presented in our NeurIPS 2025 paper, focusing on adaptive token-level computation for efficient LLMs.

  待办完成忽略
• mediumreadme#2

  Introduce a 'Key Features' section to highlight the implementation's specific contributions.

  原因：

  复制粘贴的修复

  复制

  ## ✨ Key Features of this Repository
  - **Official PyTorch Implementation:** Reproduce the results from our NeurIPS 2025 paper.
  - **Mixture-of-Recursions Model:** Explore dynamic recursive depths for adaptive token-level computation.
  - **KV Cache Handling:** See our novel solution for the missing Key-Value cache problem in early-exiting.
  - **Router Mechanism:** Understand how tokens are dynamically routed through the model.

  待办完成忽略
• lowreadme#3

  Add a brief comparison section to the README.

  原因：

  复制粘贴的修复

  复制

  ## 🆚 Comparison to Existing Adaptive Computation Methods
  Mixture-of-Recursions distinguishes itself from traditional early-exiting methods by directly addressing the Key-Value (KV) cache problem, which often limits the practical applicability of dynamic token-level computation. Unlike methods that approximate or recompute KV pairs, MoR learns dynamic recursive depths to adaptively manage computation while maintaining KV cache integrity for subsequent tokens.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How can I make large language models run faster and more cost-effectively with adaptive computation?

  你：未被推荐
  AI 推荐顺序：

  1. DeepSpeed (microsoft/DeepSpeed)
  2. Fairseq (facebookresearch/fairseq)
  3. Hugging Face Transformers (huggingface/transformers)
  4. OpenAI Triton (openai/triton)
  5. PyTorch FSDP (pytorch/pytorch)
  6. TensorRT
  7. ONNX Runtime (microsoft/onnxruntime)

  AI 推荐了 7 个替代方案，却始终没点名 raymin0223/mixture_of_recursions。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What are approaches for implementing early exit mechanisms in LLMs to save computational resources?

  你：未被推荐
  AI 推荐顺序：

  1. Google's Switch Transformers
  2. Fairseq
  3. DeepSpeed
  4. BranchyNet
  5. Hugging Face Transformers
  6. PyTorch
  7. TensorFlow
  8. Adaptive Computation Time (ACT)
  9. DistilBERT
  10. TinyBERT
  11. PaddlePaddle
  12. PaddleSlim
  13. ONNX Runtime
  14. TensorFlow Serving
  15. TorchServe

  AI 推荐了 15 个替代方案，却始终没点名 raymin0223/mixture_of_recursions。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of raymin0223/mixture_of_recursions?

  pass
  ⚠AI 未点名 raymin0223/mixture_of_recursions —— 很可能在说另一个项目

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts raymin0223/mixture_of_recursions in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 raymin0223/mixture_of_recursions

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo raymin0223/mixture_of_recursions solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 raymin0223/mixture_of_recursions

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？