2024年终大放送 之 TOP30论文榜：
No 1. [CL]《Reinforcement Learning Enhanced LLMs: A Survey》
网页链接
No 2. [CL]《HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction》网页链接
No 3. [AI]《LLM Agent Operating System》网页链接
No 4. [CL]《How to Train Data-Efficient LLMs》网页链接
No 5. [LG]《Transformers on Markov Data: Constant Depth Suffices》网页链接
No 6. [CL]《LLM Pruning and Distillation in Practice: The Minitron Approach》网页链接
No 7. [LG]《Prompt Design and Engineering: Introduction and Advanced Methods》网页链接
No 8. [LG]《softmax is not enough (for sharp out-of-distribution)》网页链接
No 9. [CL]《Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks》网页链接
No 10. [CV]《Segment Anything without Supervision》网页链接
No 11. [IR]《Is Cosine-Similarity of Embeddings Really About Similarity?》网页链接
No 12. [LG]《Deep Learning for Economists》网页链接
No 13. [LG]《KAN: Kolmogorov-Arnold Networks》网页链接
No 14. [LG]《Reasoning Algorithmically in Graph Neural Networks》网页链接
No 15. [LG]《Solving olympiad geometry without human demonstrations》网页链接
No 16. [CL]《Don't Forget to Connect! Improving RAG with Graph-based Reranking》网页链接
No 17. [LG]《How Transformers Learn Causal Structure with Gradient Descent》网页链接
No 18. [LG]《Masked Attention is All You Need for Graphs》网页链接
No 19. [CL]《Chain-of-Thought Reasoning Without Prompting》网页链接
No 20. [CL]《Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together》网页链接
No 21. [CL]《Transformers Can Represent nn-gram Language Models》
网页链接
No 22. [LG]《Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective》 网页链接
No 23. [IR]《Meta Knowledge for Retrieval Augmented Large Language Models》 网页链接
No 24. [CL]《Mixtral of Experts》 网页链接
No 25. [LG]《Text2SQL is Not Enough: Unifying AI and Databases with TAG》 网页链接
No 26. [LG]《xLSTMTime : Long-term Time Series Forecasting With xLSTM》 网页链接
No 27. [LG]《MCMC-driven learning》 网页链接
No 28. [LG]《Fast Inference of Mixture-of-Experts Language Models with Offloading》 网页链接
No 29. [CL]《Searching for Best Practices in Retrieval-Augmented Generation》 网页链接
No 30. [CV]《Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model》 网页链接
#人工智能##AI创造营##论文#
No 1. [CL]《Reinforcement Learning Enhanced LLMs: A Survey》
网页链接No 2. [CL]《HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction》
网页链接No 3. [AI]《LLM Agent Operating System》
网页链接No 4. [CL]《How to Train Data-Efficient LLMs》
网页链接No 5. [LG]《Transformers on Markov Data: Constant Depth Suffices》
网页链接No 6. [CL]《LLM Pruning and Distillation in Practice: The Minitron Approach》
网页链接No 7. [LG]《Prompt Design and Engineering: Introduction and Advanced Methods》
网页链接No 8. [LG]《softmax is not enough (for sharp out-of-distribution)》
网页链接No 9. [CL]《Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks》
网页链接No 10. [CV]《Segment Anything without Supervision》
网页链接No 11. [IR]《Is Cosine-Similarity of Embeddings Really About Similarity?》
网页链接No 12. [LG]《Deep Learning for Economists》
网页链接No 13. [LG]《KAN: Kolmogorov-Arnold Networks》
网页链接No 14. [LG]《Reasoning Algorithmically in Graph Neural Networks》
网页链接No 15. [LG]《Solving olympiad geometry without human demonstrations》
网页链接No 16. [CL]《Don't Forget to Connect! Improving RAG with Graph-based Reranking》
网页链接No 17. [LG]《How Transformers Learn Causal Structure with Gradient Descent》
网页链接No 18. [LG]《Masked Attention is All You Need for Graphs》
网页链接No 19. [CL]《Chain-of-Thought Reasoning Without Prompting》
网页链接No 20. [CL]《Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together》
网页链接No 21. [CL]《Transformers Can Represent nn-gram Language Models》
网页链接No 22. [LG]《Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective》
网页链接No 23. [IR]《Meta Knowledge for Retrieval Augmented Large Language Models》
网页链接No 24. [CL]《Mixtral of Experts》
网页链接No 25. [LG]《Text2SQL is Not Enough: Unifying AI and Databases with TAG》
网页链接No 26. [LG]《xLSTMTime : Long-term Time Series Forecasting With xLSTM》
网页链接No 27. [LG]《MCMC-driven learning》
网页链接No 28. [LG]《Fast Inference of Mixture-of-Experts Language Models with Offloading》
网页链接No 29. [CL]《Searching for Best Practices in Retrieval-Augmented Generation》
网页链接No 30. [CV]《Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model》
网页链接#人工智能##AI创造营##论文#
