Bibliografía

Papers open-access descargados en references/papers/<key>/(no versionados en git). Config: references/papers_config.json.

37 PDFs locales disponibles vía arXiv.

Catálogo local

• schulhoff2024prompt — The Prompt Report · arXiv:2406.06608
• kapoor2024agents — AI Agents That Matter · arXiv:2407.01502
• brown2020fewshot — Language Models are Few-Shot Learners · arXiv:2005.14165
• wei2022cot — Chain-of-Thought Prompting · arXiv:2201.11903
• yao2023react — ReAct · arXiv:2210.03629
• yao2023tot — Tree of Thoughts · arXiv:2305.10601
• schick2023toolformer — Toolformer · arXiv:2302.04761
• zheng2023judge — Judging LLM-as-a-Judge · arXiv:2306.05685
• greshake2023injection — Not what you've signed up for · arXiv:2302.12173
• sclar2024sensitivity — Quantifying language models sensitivity · arXiv:2310.11324
• wang2023selfconsistency — Self-Consistency Improves CoT · arXiv:2203.11171
• wu2023autogen — AutoGen · arXiv:2308.08155
• perez2022ignore — Ignore Previous Prompt · arXiv:2211.09527
• shinn2023reflexion — Reflexion · arXiv:2303.11366
• vaswani2017attention — Attention Is All You Need · arXiv:1706.03762
• hu2022lora — LoRA · arXiv:2106.09685
• lewis2020rag — Retrieval-Augmented Generation · arXiv:2005.11401
• ouyang2022instruct — Training language models to follow instructions · arXiv:2203.02155
• bommasani2021foundation — On the Opportunities and Risks of Foundation Models · arXiv:2108.07258
• carlini2021extracting — Extracting Training Data from Large Language Models · arXiv:2012.07805
• dettmers2023qlora — QLoRA · arXiv:2305.14314
• liu2024lostmiddle — Lost in the Middle · arXiv:2307.03172
• rafailov2023dpo — Direct Preference Optimization · arXiv:2305.18290
• kleinberg2015prediction — Prediction Policy Problems · arXiv:
• paleyes2022challenges — Challenges in Deploying Machine Learning · arXiv:2011.09926
• gao2024ragsurvey — RAG for LLMs: A Survey · arXiv:2312.10997
• zaharia2024compound — The Shift from Models to Compound AI Systems · arXiv:
• huyen2022designing — Designing Machine Learning Systems · arXiv:
• amershi2019se4ml — Software Engineering for Machine Learning · arXiv:
• bucinca2021trust — To Trust or to Think · arXiv:2102.09692
• sambasivan2021datacascades — Data Cascades in High-Stakes AI · arXiv:
• breck2017mltest — The ML Test Score · arXiv:
• parasuraman2000automation — Types and Levels of Human Interaction with Automation · arXiv:
• kreuzberger2023mlops — MLOps Overview · arXiv:2205.02302
• gama2014conceptdrift — Concept Drift Adaptation Survey · arXiv:
• beyer2016sre — Site Reliability Engineering · arXiv:
• burns2022kubernetes — Kubernetes Up and Running · arXiv:

Por curso (syllabi)

09 Prompt Engineering — obligatoria

• brown2020fewshot, greshake2023injection, kapoor2024agents, schulhoff2024prompt, wei2022cot, yao2023react, zheng2023judge

08 GenAI / LLMs — selección

• vaswani2017attention, brown2020fewshot, ouyang2022instruct, hu2022lora, lewis2020rag, bommasani2021foundation, dettmers2023qlora, liu2024lostmiddle, rafailov2023dpo, zheng2023judge

Labs: herramientas locales.