#ai #promptengineering #evolution Promptbreeder is a self-improving self-referential system for automated prompt engineering. Give it a task description and a dataset, and it will automatically come up with appropriate prompts for the task. This is achieved by an evolutionary algorithm where not only the prompts, but also the mutation-prompts are improved over time in a population-based, diversity-focused approach. OUTLINE: 0:00 - Introduction 2:10 - From manual to automated prompt engineering 10:40 - How does Promptbreeder work? 21:30 - Mutation operators 36:00 - Experimental Results 38:05 - A walk through the appendix Paper: https://arxiv.org/abs/2309.16797 Abstract: Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-optimal. In this paper, we present Promptbreeder, a general-purpose self-referential self-improvement mechanism that evolves and adapts prompts for a given domain. Driven by an LLM, Promptbreeder mutates a population of task-prompts, and subsequently evaluates them for fitness on a training set. Crucially, the mutation of these task-prompts is governed by mutation-prompts that the LLM generates and improves throughout evolution in a self-referential way. That is, Promptbreeder is not just improving task-prompts, but it is also improving the mutationprompts that improve these task-prompts. Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. Furthermore, Promptbreeder is able to evolve intricate task-prompts for the challenging problem of hate speech classification. Authors: Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rocktäschel Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n ... https://www.youtube.com/watch?v=tkX0EfNl4Fc

OUTLINE: 0:30 - Activity Grammars for Temporal Action Segmentation 8:50 - Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback 17:05 - On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences 21:20 - Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming 27:10 - Equivariant Adaptation of Large Pretrained Models 33:10 - Multi-Head Adapter Routing for Cross-Task Generalization 39:25 - Geometry-Aware Adaptation for Pretrained Models 46:10 - Adversarial Learning for Feature Shift Detection and Correction Papers: Title: Activity Grammars for Temporal Action Segmentation Link: https://arxiv.org/abs/2312.04266 Author: Dayoung Gong, Joonseok Lee, Deunsol Jung, Suha Kwak, Minsu Cho -------- Title: Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback Link: https://arxiv.org/abs/2311.16102 Author: Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li, Deepak Pathak, Katerina Fragkiadaki -------- Title: On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences Link: https://arxiv.org/abs/2305.18423 Author: Alireza Fathollah Pour, Hassan Ashtiani -------- Title: Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming Link: https://arxiv.org/abs/2310.19068 Author: Gregory Dexter, Petros Drineas, David P. Woodruff, Taisuke Yasuda -------- Title: Equivariant Adaptation of Large Pretrained Models Link: https://arxiv.org/pdf/2310.01647.pdf Author: Arnab Kumar Mondal, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Sai Rajeswar, Siamak Ravanbakhsh -------- Title: Multi-Head Adapter Routing for Cross-Task Generalization Link: https://arxiv.org/abs/2211.03831 Author: Lucas Caccia, Edoardo Ponti, Zhan Su, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni -------- Title: Geometry-Aware Adaptation for Pretrained Models Link: https://arxiv.org/abs/2307.12226 Author: Nicholas Roberts, Xintong Li, Dyah Adila, Sonia Cromp, Tzu-Heng Huang, Jitian Zhao, Frederic Sala -------- Title: Adversarial Learning for Feature Shift Detection and Correction Link: https://arxiv.org/abs/2312.04546 Author: Miriam Barrabes, Daniel Mas Montserrat, Margarita Geleta, Xavier Giro-i-Nieto, Alexander G. Ioannidis Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n ... https://www.youtube.com/watch?v=cx3bbMf9LRA

#lumiere #texttovideoai #google LUMIERE by Google Research tackles globally consistent text-to-video generation by extending the U-Net downsampling concept to the temporal axis of videos. OUTLINE: 0:00 - Introduction 8:20 - Problems with keyframes 16:55 - Space-Time U-Net (STUNet) 21:20 - Extending U-Nets to video 37:20 - Multidiffusion for SSR prediction fusing 44:00 - Stylized generation by swapping weights 49:15 - Training & Evaluation 53:20 - Societal Impact & Conclusion Paper: https://arxiv.org/abs/2401.12945 Website: https://lumiere-video.github.io/ Abstract: We introduce Lumiere -- a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse and coherent motion -- a pivotal challenge in video synthesis. To this end, we introduce a Space-Time U-Net architecture that generates the entire temporal duration of the video at once, through a single pass in the model. This is in contrast to existing video models which synthesize distant keyframes followed by temporal super-resolution -- an approach that inherently makes global temporal consistency difficult to achieve. By deploying both spatial and (importantly) temporal down- and up-sampling and leveraging a pre-trained text-to-image diffusion model, our model learns to directly generate a full-frame-rate, low-resolution video by processing it in multiple space-time scales. We demonstrate state-of-the-art text-to-video generation results, and show that our design easily facilitates a wide range of content creation tasks and video editing applications, including image-to-video, video inpainting, and stylized generation. Authors: Omer Bar-Tal, Hila Chefer, Omer Tov, Charles Herrmann, Roni Paiss, Shiran Zada, Ariel Ephrat, Junhwa Hur, Yuanzhen Li, Tomer Michaeli, Oliver Wang, Deqing Sun, Tali Dekel, Inbar Mosseri Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n ... https://www.youtube.com/watch?v=Pl8BET_K1mc

#openai #samaltman #coup After his spectacular firing yesterday, investors and employees are pressuring OpenAI's board of directors to reinstate Sam Altman back as CEO. References: https://twitter.com/gdb/status/1725736242137182594 https://arstechnica.com/information-technology/2023/11/report-sutskever-led-board-coup-at-openai-that-ousted-altman-over-ai-safety-concerns/?utm_medium=social&utm_source=twitter&utm_social-type=owned&utm_brand=ars https://www.axios.com/2023/11/18/openai-memo-altman-firing-malfeasance-communications-breakdown https://www.theinformation.com/articles/openais-86-billion-share-sale-in-jeopardy-following-altman-firing https://www.wired.com/story/openai-sam-altman-ousted-what-happened/ https://www.theinformation.com/articles/openai-co-founder-altman-plans-new-venture https://www.bloomberg.com/news/articles/2023-11-18/openai-board-being-pressed-by-some-investors-to-reinstate-altman?utm_source=twitter&utm_campaign=socialflow-organic&utm_medium=social&utm_content=business&cmpid=socialflow-twitter-business#xj4y7vzkg https://www.theverge.com/2023/11/18/23967199/breaking-openai-board-in-discussions-with-sam-altman-to-return-as-ceo https://www.theinformation.com/articles/altman-decision-looms-as-sequoia-tiger-negotiate-behind-scenes https://twitter.com/deliprao/status/1726126676990456212 https://twitter.com/Simeon_Cps/status/1725958642405400896 https://twitter.com/gdb https://twitter.com/sama/status/1726099792600903681/quotes https://twitter.com/kyutai_labs/status/1725483921041760323 https://www.theverge.com/2023/11/18/23966980/meta-disbanded-responsible-ai-team-artificial-intelligence Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n ... https://www.youtube.com/watch?v=-SWONSNzJGo