[CoT]Paper List
Chain-of-Thought(SAM) Paper List
- Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
- Plan-and-Solve Prompting, Improving Zero-Shot Chain-of-Thought
참고
[SSM] Modeling Sequences with Structured State Spaces - Part I
10 분 소요
1.1 Deep sequence model Definition 1.1 (Informal). We use sequence model to refer to a parameterized map on sequences $y=f_\theta(x)$ where inputs and o...
[LLM-RL] Lecture 2: Value Functions
2 분 소요
Overview. This post focuses on Value Functions in reinforcement learning. We begin with a quick recap of the RL setup, then introduce state-value / action-va...
[Paper] LLM‑JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
2 분 소요
This is a brief review for “LLM‑JEPA: Large Language Models Meet Joint Embedding Predictive Architectures”. You can see the paper at this link.
[LLM-RL] Lecture 1: MDP, Objective, Value Functions, and Imitation Learning
3 분 소요
Overview. This post builds from the MDP framework to the RL objective and value functions, then contrasts pure RL with Imitation Learning (IL), focusing on B...
댓글남기기