Reading List

1. LLMs Basics:

• Attention Is All You Need. Vaswani, et al. https://arxiv.org/abs/1706.03762
• OpenAI o1 System Card. OpenAI. https://cdn.openai.com/o1-system-card-20241205.pdf?utm_source=chatgpt.com.  

2. Multimodal LLMs 

• Learning Transferable Visual Models From Natural Language Supervision. Radford, et al. https://arxiv.org/abs/2103.00020.
• Llava: Visual Instruction Tuning. Liu, et al. https://arxiv.org/abs/2304.08485.

3. Software Engineering Benchmarks for LLMs

• SWE-bench: Can Language Models Resolve Real-World GitHub Issues? Jimenez, et al. https://arxiv.org/abs/2310.06770.  
• SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? Yang, et al. https://arxiv.org/abs/2410.03859. 

4. Multimodal LLMs for Front-End Development 

• Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering. Si, et al. https://arxiv.org/abs/2403.03163. 
• Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping. Li, et al. https://arxiv.org/abs/2410.16232. 

5. LLMs as Programming Agents

• OpenHands: An Open Platform for AI Software Developers as Generalist Agents. Wang, et al. https://arxiv.org/abs/2407.16741. 
• ChatDev: Communicative Agents for Software Development. Qian, et al. https://arxiv.org/abs/2307.07924.

6. LLMs Augmented with Tools

• Augmented Language Models: a Survey. Mialon, et al. https://arxiv.org/abs/2302.07842.
• ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback. Wu et al. https://arxiv.org/abs/2409.14826. 

7. LLMs for Testing

• Automated Unit Test Improvement using Large Language Models at Meta. Alshahwan and et al. https://arxiv.org/abs/2402.09171.
• Teaching Large Language Models to Self-Debug. Chen, et al. https://arxiv.org/abs/2304.05128.

8. Reasoning with LLMs

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Wei, et al. https://arxiv.org/abs/2201.11903.
• Chain of Code: Reasoning with a Language Model-Augmented Code Emulator. Li, et al. https://arxiv.org/abs/2312.04474. 

9. LLMs for Theorem Proving

• Generative Language Modeling for Automated Theorem Proving. Polu and Sutskever. https://arxiv.org/abs/2009.03393.
• Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically. Dong, et al. https://arxiv.org/abs/2411.01829.

10. Security and Trustworthiness of LLMs

• Identifying and Mitigating the Security Risks of Generative AI.  Barrett, et al. https://arxiv.org/abs/2308.14840. 

· TRUSTLLM: Trustworthiness in Large Language Models. Huang et al. https://arxiv.org/abs/2401.05561.