Learning Journey on Informatics 2026
Keywords:
Sustainable Computing, Generative Artificial Intelligence, Large Language Models (LLMs), Prompt Engineering, Diffusion Models, Image Synthesis, User-Centered Software Development, User Experience (UX), Carbon Footprint, Energy ConsumptionSynopsis
In the 2026 edition of the Learning Journey on Informatics (Jornada de Atualização em Informática – JAI), we present a diverse collection of texts prepared as supporting material for the tutorials selected for the event held during CSBC 2026. In its 45th edition, JAI reaffirms its academic importance as a forum dedicated to the scientific and technological advancement of the Brazilian Computing community. The texts gathered in this volume provide a comprehensive and up-to-date overview of topics that are highly relevant to both Computing research and professional practice. Although they address distinct subjects, they share a common goal: to present concepts, methods, and tools related to contemporary topics of great significance for the development of technological solutions capable of generating a positive impact on society.
The first chapter focuses on Sustainable Computing, a topic of growing importance given the expansion of digital infrastructures and the increasing energy consumption associated with information technologies. The authors discuss the socio-environmental impacts of computing, present metrics and tools for measuring energy consumption and the carbon footprint, and explore strategies for developing more efficient and environmentally responsible applications. By emphasizing the need to incorporate sustainability into software development processes and the education of computing professionals, the chapter contributes to fostering a broader understanding of the role of Computing in building a sustainable future.
The second chapter introduces diffusion models, the technology that currently underpins many of the advances in AI-generated image and video synthesis. In an accessible yet technically rigorous manner, the text guides readers through the probabilistic and computational foundations of these models, explaining how diffusion and denoising processes enable the generation of high-quality visual content from textual descriptions. By presenting the principles underlying widely used contemporary systems, the chapter provides a didactic introduction to one of the most significant topics in generative artificial intelligence.
The third chapter shifts the focus from technology to people by presenting a user-centered approach to software development. Drawing on the authors' extensive experience, the text describes the b_thinking model, which integrates UX practices, Design Thinking, Lean UX, and Agile methodologies into a framework aimed at creating digital products that effectively meet users' needs. More than a collection of techniques, the chapter proposes a development culture grounded in empathy, collaboration, continuous validation, and shared learning, demonstrating that technological excellence also depends on a deep understanding of the human contexts in which software is used.
Concluding the volume, the fourth chapter addresses prompt optimization in large language models, a topic that has gained enormous relevance with the widespread adoption of generative artificial intelligence systems. The authors present the foundations of prompt engineering and optimization, discuss strategies such as zero-shot, few-shot, and chain-of-thought prompting, explore advanced techniques for adaptation and evaluation, and analyze challenges related to the robustness, security, and reliability of these systems. The chapter offers a current and critical perspective on the mechanisms that enable the effective guidance of large language models and enhance their performance across a wide range of applications.
Taken together, the chapters illustrate part of the breadth and diversity of today's challenges in Computing, spanning issues of sustainability and socio-environmental impact, user-centered software development, the foundations of generative artificial intelligence, and advanced techniques for interacting with large language models.
We would like to thank the authors for their dedication in preparing these chapters and the reviewers of the tutorial proposals for their careful work throughout the selection process, which sought to identify, among the submitted proposals, those that best met criteria such as scientific relevance, innovation, topicality, authors' expertise, regional representation, and institutional diversity.
We hope that these texts will inspire reflection, stimulate new research, and contribute to the education of researchers and professionals committed to developing innovative, ethical, inclusive technologies that are aligned with the needs of society.
Chapters
-
1. Sustainable Computing: From Theory to Practice with Tools for Measuring Energy Consumption and the Carbon Footprint of Applications
-
2. Introduction to Diffusion Models for Image Synthesis
-
3. User-Centered Software Development: Building Products with Design Thinking, UX, and Agile
-
4. Prompt Optimization in Large Language Models: Techniques, Evaluation, and Challenges
Downloads
References
Alibaba. Wan video. AI video generator, 2026. URL [link]. Last Access, May 2026.
Almeida, G., Torres Do Ó, M., Francesquini, E., and Cordeiro, D. (2024). Reducing carbon emissions of distributed systems: a multi-objective approach. In Proceedings of the 20th Brazilian Symposium on Information Systems, pages 1–10.
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, !ukasz Kaiser, and Illia Polosukhin. Attention is All You Need. NeurIPS, 30, 2017.
Banerjee, S. e Lavie, A. (2005). METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. Em Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, p. 65–72.
Bono, E. Six Thinking Hats. 1999.
Brasil. Lei nº 13.709, de 14 ago. 2018. Lei Geral de Proteção de Dados Pessoais (LGPD). Diário Oficial da União, p. 59-59, 2018.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A. et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
Cadorel, E. and Saingre, D. (2024). A protocol to assess the accuracy of process-level power models. In 2024 IEEE International Conference on Cluster Computing (CLUSTER), pages 74–84. IEEE.
Campos, G. A., Andreoni, M. e Mattos, D. M. F. (2026). Avaliação da herança de propriedades adversariais em grandes modelos de linguagem com restrição de contexto e destilação de conhecimento latente. Em Anais do SEMISH 2026 - LIII Seminário Integrado de Software e Hardware, Gramado, RS. Sociedade Brasileira de Computação. A ser publicado.
Carro, L. and Nazar, G. L. (2023). Desafios para a computação energeticamente eficiente. Sociedade Brasileira de Computação.
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., Ye, W., Zhang, Y., Chang, Y., Yu, P. S., Yang, Q. e Xie, X. (2024). A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol., 15(3).
Chaudhari, S., Aggarwal, P., Murahari, V., Rajpurohit, T., Kalyan, A., Narasimhan, K., Deshpande, A. e Castro da Silva, B. (2025). Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms. ACM Computing Surveys, 58(2):1–37. Otimização de Prompts em Modelos de Linguagem em Larga Escala: Técnicas, Avaliação e Desafios
Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. SDEdit: Guided image synthesis and editing with stochastic differential equations. In International Conference on Learning Representations, 2022. URL [link].
ChenWang, Hao-Yang Peng, Ying-Tian Liu, Jiatao Gu, and Shi-Min Hu. Diffusion models for 3d generation: A survey. Computational Visual Media, 11 (1):1–28, 2025.
Chitwan Saharia,William Chan, et al. Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, 35:36479–36494, 2022.
Cordeiro, D., Francesquini, E., Amarís, M., Castro, M., Baldassin, A., and Lima, J. (2023). Green cloud computing: Challenges and opportunities. In Anais Estendidos do XIX Simpósio Brasileiro de Sistemas de Informação, pages 129–131, Porto Alegre, RS, Brasil. SBC.
Cui, W., Zhang, J., Li, Z., Sun, H., Lopez, D., Das, K., Malin, B. A. e Kumar, S. (2025). Automatic prompt optimization via heuristic search: A survey. arXiv preprint arXiv:2502.18746.
Deevid AI. Deevid. AI video generator, 2026. URL [link]. Last Access, May 2026.
Diamond, J. and Stoico, V. (2026). What is the cost of energy monitoring? an empirical study on the overhead of rapl-based tools. arXiv preprint arXiv:2604.26815.
Diederik P. Kingma and Max Welling. Auto-Encoding Variational Bayes. In 2nd Intern. Conf. on Learning Representations, ICLR 2014, 2014.
Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y. e He, L. (2026). A survey on the optimization of large language model-based agents. ACM Computing Surveys, 58(9):1–37.
Edemacu, K. e Wu, X. (2025). Privacy preserving prompt engineering: A survey. ACM Computing Surveys, 57(10):1–36.
Gustavo Lopes Tamiosso, Caetano Müller, Lucas Spagnolo Bombana, and Manuel M Oliveira. Memory-efficient filter-guided diffusion with domain transform filtering. Computers & Graphics, page 104389, 2025.
Hoffmann, H. (2015). Jouleguard: Energy guarantees for approximate applications. In Proceedings of the 25th Symposium on Operating Systems Principles, pages 198–214.
Inc Runway AI. Runway gen 4.5. AI video generator, 2026. URL [link]. Last Access, May 2026.
Jain, A. M. e Jindal, M. (2025). Systematic survey of various prompt optimization methods and their classifications. Em 2025 11th International Conference on Computing and Artificial Intelligence (ICCAI), p. 524–536. IEEE.
James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, et al. Improving image generation with better captions. Computer Science. [link], 2(3):8, 2023.
Jascha Sohl-Dickstein, EricWeiss, Niru Maheswaranathan, and Surya Ganguli. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, pages 2256–2265. pmlr, 2015.
Jay, M., Ostapenco, V., Lefèvre, L., Trystram, D., Orgerie, A.-C., and Fichel, B. (2023). An experimental comparison of software-based power meters: focus on CPU and GPU. In 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pages 106–118. IEEE.
Jiaming Song, Chenlin Meng, and Stefano Ermon. Denoising diffusion implicit models. In International Conference on Learning Representations, 2021. URL [link].
Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. NeurIPS, 33:6840–6851, 2020.
Jones, N. et al. (2018). How to stop data centres from gobbling up the worlds electricity. Nature, 561(7722):163–166.
Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, and Sungroh Yoon. Ilvr: Conditioning method for denoising diffusion probabilistic models. In Proceedings of ICCV, pages 14367–14376, 2021.
Josh Abramson, Jonas Adler, et al. Accurate structure prediction of biomolecular interactions with alphafold 3. Nature, 630(8016):493–500, 2024.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proc. of CVPR, pages 770–778, 2016.
Kavanagh, R., Armstrong, D., and Djemame, K. (2016). Accuracy of energy model calibration with IPMI. In 2016 IEEE 9th International Conference on Cloud Computing (CLOUD), pages 648–655. IEEE.
Kennes, T. (2023). Measuring IT carbon footprint: What is the current status actually? arXiv preprint arXiv:2306.10049.
Khan, K. N., Hirki, M., Niemi, T., Nurminen, J. K., and Ou, Z. (2018). RAPL in action: Experiences in using rapl for power measurements. ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS), 3(2):1–26.
Labs Black Forest. Flux. AI image generator, 2026. URL [link]. Last Access, May 2026.
Launikas, A. E., Nakano, F., Coutinho, F. L., Cordeiro, D., et al. (2024). Evolução histórica do desempenho energético de tarefas cotidianas em uma distribuição Linux. In Simpósio em Sistemas Computacionais de Alto Desempenho (SSCAD), pages 81–88. SBC.
Lee, Y. C. and Zomaya, A. Y. (2012). Energy efficient utilization of resources in cloud computing systems. The Journal of Supercomputing, 60(2):268–280.
Li, Y. (2023). A practical survey on zero-shot prompt design for in-context learning. Em Proceedings of the 14th international conference on recent advances in natural language processing, p. 641–647.
Li, Z., Liu, Y., Su, Y. e Collier, N. (2025a). Prompt compression for large language models: A survey. Em Chiruzzo, L., Ritter, A. e Wang, L., editors, Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), p. 7182–7195, Albuquerque, New Mexico. Association for Computational Linguistics.
Li, Z., Su, Y. e Collier, N. (2025b). A survey on prompt tuning. arXiv preprint arXiv:2507.06085.
Liu, Z. (2025). Reinforcement learning for prompt optimization in language models: A comprehensive survey of methods, representations, and evaluation challenges. ICCK Transactions on Emerging Topics in Artificial Intelligence, 2(4):173–181.
Lottick, K., Susai, S., Friedler, S. A., and Wilson, J. P. (2019). Energy usage reports: Environmental awareness as part of algorithmic accountability. arXiv preprint arXiv:1911.08354.
Luma Labs. Luma dream machine. AI video generator, 2026. URL [link]. Last Access, May 2026.
Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. Gans trained by a two time-scale update rule converge to a local nash equilibrium. NeurIPS, 30, 2017.
McCullough, J. C., Agarwal, Y., Chandrashekar, J., Kuppuswamy, S., Snoeren, A. C., Gupta, R. K., et al. (2011). Evaluating the effectiveness of model-based power characterization. In USENIX Annual Technical Conf, volume 20, pages 19–20.
Midjourney, Inc. Midjourney. AI image generator, 2026. URL [link]. Last Access, May 2026.
Möbius, C., Dargie, W., and Schill, A. (2013). Power consumption estimation models for processors, virtual machines, and servers. IEEE Transactions on Parallel and Distributed Systems, 25(6):1600–1614.
Moia, V. H. G., Sanz, I. J., Rebello, G. A. F., de Meneses, R. D., Hitaj, B. e Lindqvist, U. (2026). Llm in the middle: A systematic review of threats and mitigations to real-world llm-based systems. Computer Science Review, 61:100916.
Nafus, D., Schooler, E. M., and Burch, K. A. (2021). Carbonresponsive computing: Changing the nexus between energy and computing. Energies, 14(21):6917.
Nielsen, Jakob (2012). How Many Test Users in a Usability Study? Disponível em: [link] Acesso em 22 jun. 2026.
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. Unet: Convolutional networks for biomedical image segmentation. In Intern. Conf. on Medical image computing and computer-assisted intervention, pages 234–241, 2015.
Open AI. Nano banana pro. AI image generator, 2026. URL [link]. Last Access, May 2026.
OpenAI. Sora 2. AI video generator, 2026. URL [link]. Last Access, May 2026.
Osborn, A. Applied imagination: principles and procedures of creative thinking. New York: Scribner, 1979.
Paul, S. G., Saha, A., Arefin, M. S., Bhuiyan, T., Biswas, A. A., Reza, A. W., Alotaibi, N. M., Alyami, S. A., and Moni, M. A. (2023). A comprehensive review of green computing: Past, present, and future research. IEEE access, 11:87445–87494.
Pernice, K.; Gibbons, S.; Moran, K.; Whitenton, K. (2021) The 6 Levels of UX Maturity. Nielsen Norman Group. Disponível em: [link] Acesso em: 21 ago. 2023.
Phung, J., Lee, Y. C., and Zomaya, A. Y. (2018). Modeling systemlevel power consumption profiles using RAPL. In 2018 IEEE 17th International Symposium on Network Computing and Applications (NCA), pages 1–4. IEEE.
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. High-resolution image synthesis with latent diffusion models. In Proceedings of CVPR, pages 10684–10695, 2022.
Rocha, F. W., Fukuda, J. C., Francesquini, E., and Cordeiro, D. (2022). Accelerating smart city simulations. In Gitler, I., Barrios Hernández, C. J., and Meneses, E., editors, High Performance Computing, pages 148–162, Cham. Springer International Publishing.
Saleem, S., Asim, M. N., Zulfiqar, S. e Dengel, A. (2026). The evolution of natural language processing: How prompt optimization and language models are shaping the future. Computer Science Review, 61:100938.
Sandoval, G., Pearce, H., Nys, T., Karri, R., Garg, S. e Dolan-Gavitt, B. (2023). Lost at c: A user study on the security implications of large language model code assistants. Em 32nd USENIX Security Symposium (USENIX Security 23), p. 2205–2222, Anaheim, CA. USENIX Association.
Santos, A. L. d. M. and Wagner, F. R., editors (2025). Grandes Desafios da Computação no Brasil 2025-2035. Sociedade Brasileira de Computação (SBC), Porto Alegre.
Sharma, R., Mehta, M. e Raina, S. T. (2025). Rlhf: A comprehensive survey for cultural, multimodal and low latency alignment methods. Em International Conference on Computing and Communication Networks, p. 230–246. Springer. Otimização de Prompts em Modelos de Linguagem em Larga Escala: Técnicas, Avaliação e Desafios
Shitong Luo and Wei Hu. Diffusion probabilistic models for 3d point cloud generation. In Proceedings of CVPR, pages 2837–2845, 2021.
Singla, A., Sukharevsky, A., Hall, B., Yee, L., Chui, M. e Balakrishnan, T. (2025). The state of AI in 2025: Agents, innovation, and transformation. Technical report, QuantumBlack, AI by McKinsey.
Sui, Y., Chuang, Y.-N., Wang, G., Zhang, J., Zhang, T., Yuan, J., Liu, H., Wen, A., Zhong, S., Zou, N. et al. (2025). Stop overthinking: A survey on efficient reasoning for large language models. arXiv preprint arXiv:2503.16419.
Technology Kuaishou. Klingai. AI video generator, 2026. URL [link]. Last Access, May 2026.
Thamm, P. and Leser, U. (2025). Strategies to measure energy consumption using RAPL during workflow execution on commodity clusters. arXiv preprint arXiv:2505.09375.
Tian, K., Mitchell, E., Zhou, A., Sharma, A., Rafailov, R., Yao, H., Finn, C. e Manning, C. D. (2023). Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975.
Vasconcelos, M., Cordeiro, D., Da Costa, G., Dufossé, F., Nicod, J.-M., and Rehn-Sonigo, V. (2023). Optimal sizing of a globally distributed low carbon cloud federation. In 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pages 203–215. IEEE.
Wang, J., Hu, X., Hou, W., Chen, H., Zheng, R., Wang, Y., Yang, L., Huang, H., Ye,W., Geng, X. et al. (2023). On the robustness of chatgpt: An adversarial and out-of-distribution perspective. arXiv preprint arXiv:2302.12095.
Wazlawick, R. S.; Santos, R. A.; Hammes, J. F.; Cunha, C. L. Desenvolvimento de Software Centrado no Usuário: Construindo produtos com b_thinking, UX e agile. 1. ed. Florianópolis: UFSC, 2025. v. 1. 343p.
Weaver, V. M., Johnson, M., Kasichayanula, K., Ralph, J., Luszczek, P., Terpstra, D., and Moore, S. (2012). Measuring energy and power with PAPI. In 2012 41st international conference on parallel processing workshops, pages 262–268. IEEE.
William Peebles and Saining Xie. Scalable diffusion models with transformers. In Proceedings of ICCV, pages 4195–4205, 2023.
Yang Song and Stefano Ermon. Generative modeling by estimating gradients of the data distribution. NeurIPS, 32, 2019.
Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., Zhong, S., Yin, B. e Hu, X. (2024). Harnessing the power of LLMs in practice: A survey on chatgpt and beyond. ACM Trans. Knowl. Discov. Data, 18(6).
Zeqi Gu, Ethan Yang, and Abe Davis. Filter-guided diffusion for controllable image generation. In ACM SIGGRAPH 2024 conference papers, pages 1–10, 2024.
Zhang, C., Zhou, L., Xu, X., Wu, J. e Liu, Z. (2025). Adversarial attacks of vision tasks in the past 10 years: A survey. ACM Computing Surveys, 58(2):1–42.
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. e Artzi, Y. (2020). BERTScore: Evaluating text generation with BERT. Em International Conference on Learning Representations.
Zhao, W., Peyrard, M., Liu, F., Gao, Y., Meyer, C. M. e Eger, S. (2019). MoverScore: Text generation evaluating with contextualized embeddings and earth mover distance. Em Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong, China. Association for Computational Linguistics.
Zhu, K., Wang, J., Zhou, J., Wang, Z., Chen, H., Wang, Y., Yang, L., Ye, W., Zhang, Y., Gong, N. e Xie, X. (2024). PromptRobust: Towards evaluating the robustness of large language models on adversarial prompts. Em Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis, LAMPS ’24, p. 57–68, New York, NY, USA. Association for Computing Machinery.
