论文理解【LLM-OR】——【AlphaOPT】Formulating Optimization Programs with Self-Improving LLM Experien 论文理解【LLM-OR】——【OptMATH】A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling 论文理解【LLM-OR】——【LLMOPT】Learning to Define and Solve General Optimization Problems from Scratch 论文理解【LLM-OR】——【OptiMUS】Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models 论文理解【LLM-OR】——【SIRL】Solver-Informed RL-Grounding Large Language Models for Authentic Optimization M 论文理解【LLM-OR】——【Step-Opt】Training LLMs for Optimization Modeling via Iterative Data Synthesis and 论文理解【LLM-OR】—— 【PaMOP】Guiding large language models in modeling optimization problems via question partitioning 论文理解【LLM-OR】——【ORLM】Training Large Language Models for Optimization Modeling 论文理解【LLM-OR】——【OptiTree】Hierarchical thoughts generation with tree search for LLM optimization model

论文理解【LLM-Agent】—— 【ReAct】Synergizing Reasoning and Acting in Language Models 论文理解【LLM-Agent】—— 【Reflexion】Language Agents with Verbal Reinforcement Learning 论文理解【LLM-Agent】——【SkillOpt】Executive Strategy for Self-Evolving Agent Skills

论文理解【LLM-回归】—— Decoding-based Regression 论文理解【LLM-回归】——【RAFT】Better autoregressive regression with LLMs via regression-aware fine-tuning 论文理解【LLM-回归】——【NTL】Regress, Don‘t Guess--A Regression-like Loss on Number Tokens for Language Model

论文理解【Vision Transformer】—— 【MAE】Masked Autoencoders Are Scalable Vision Learners 论文理解【Vision Transformer】——【VIT】An Image is Worth 16x16 Words-Transformers for Image Recognition at Scale 论文理解【Vision Transformer】——【Swin Transformer】Hierarchical Vision Transformer using Shifted Windows

论文理解【CV-对比学习】——【BYOL】Bootstrap Your Own Latent-A New Approach to Self-Supervised Learning 论文理解【CV-对比学习】——【SimCLR】A Simple Framework for Contrastive Learning of Visual Representations

论文理解 【LLM-RL】—— Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model 论文理解 【LLM-RL】——【EndoRM】Generalist Reward Models-Found Inside Large Language Models

论文理解【LLM-Clarification】——【QDrawer】Asking the Right Question at the Right Time