Machine Learning Street Talk (MLST)

• Sakana AI - Chris Lu, Robert Tjarko Lange, Cong Lu

  We speak with Sakana AI, who are building nature-inspired methods that could fundamentally transform how we develop AI systems.The guests include Chris Lu, a researcher who recently completed his DPhil at Oxford University under Prof. Jakob Foerster's supervision, where he focused on meta-learning and multi-agent systems. Chris is the first author of the DiscoPOP paper, which demonstrates how language models can discover and design better training algorithms. Also joining is Robert Tjarko Lange, a founding member of Sakana AI who specializes in evolutionary algorithms and large language models. Robert leads research at the intersection of evolutionary computation and foundation models, and is completing his PhD at TU Berlin on evolutionary meta-learning. The discussion also features Cong Lu, currently a Research Scientist at Google DeepMind's Open-Endedness team, who previously helped develop The AI Scientist and Intelligent Go-Explore.SPONSOR MESSAGES:***CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!https://centml.ai/pricing/Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich. Goto https://tufalabs.ai/**** DiscoPOP - A framework where language models discover their own optimization algorithms* EvoLLM - Using language models as evolution strategies for optimizationThe AI Scientist - A fully automated system that conducts scientific research end-to-end* Neural Attention Memory Models (NAMMs) - Evolved memory systems that make transformers both faster and more accurateTRANSCRIPT + REFS:https://www.dropbox.com/scl/fi/gflcyvnujp8cl7zlv3v9d/Sakana.pdf?rlkey=woaoo82943170jd4yyi2he71c&dl=0Robert Tjarko Langehttps://roberttlange.com/Chris Luhttps://chrislu.page/Cong Luhttps://www.conglu.co.uk/Sakanahttps://sakana.ai/blog/TOC:1. LLMs for Algorithm Generation and Optimization [00:00:00] 1.1 LLMs generating algorithms for training other LLMs [00:04:00] 1.2 Evolutionary black-box optim using neural network loss parameterization [00:11:50] 1.3 DiscoPOP: Non-convex loss function for noisy data [00:20:45] 1.4 External entropy Injection for preventing Model collapse [00:26:25] 1.5 LLMs for black-box optimization using abstract numerical sequences2. Model Learning and Generalization [00:31:05] 2.1 Fine-tuning on teacher algorithm trajectories [00:31:30] 2.2 Transformers learning gradient descent [00:33:00] 2.3 LLM tokenization biases towards specific numbers [00:34:50] 2.4 LLMs as evolution strategies for black box optimization [00:38:05] 2.5 DiscoPOP: LLMs discovering novel optimization algorithms3. AI Agents and System Architectures [00:51:30] 3.1 ARC challenge: Induction vs. transformer approaches [00:54:35] 3.2 LangChain / modular agent components [00:57:50] 3.3 Debate improves LLM truthfulness [01:00:55] 3.4 Time limits controlling AI agent systems [01:03:00] 3.5 Gemini: Million-token context enables flatter hierarchies [01:04:05] 3.6 Agents follow own interest gradients [01:09:50] 3.7 Go-Explore algorithm: archive-based exploration [01:11:05] 3.8 Foundation models for interesting state discovery [01:13:00] 3.9 LLMs leverage prior game knowledge4. AI for Scientific Discovery and Human Alignment [01:17:45] 4.1 Encoding Alignment & Aesthetics via Reward Functions [01:20:00] 4.2 AI Scientist: Automated Open-Ended Scientific Discovery [01:24:15] 4.3 DiscoPOP: LLM for Preference Optimization Algorithms [01:28:30] 4.4 Balancing AI Knowledge with Human Understanding [01:33:55] 4.5 AI-Driven Conferences and Paper Review

  --------  

  1:37:54
• Clement Bonnet - Can Latent Program Networks Solve Abstract Reasoning?

  Clement Bonnet discusses his novel approach to the ARC (Abstraction and Reasoning Corpus) challenge. Unlike approaches that rely on fine-tuning LLMs or generating samples at inference time, Clement's method encodes input-output pairs into a latent space, optimizes this representation with a search algorithm, and decodes outputs for new inputs. This end-to-end architecture uses a VAE loss, including reconstruction and prior losses. SPONSOR MESSAGES:***CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!https://centml.ai/pricing/Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich. Goto https://tufalabs.ai/***TRANSCRIPT + RESEARCH OVERVIEW:https://www.dropbox.com/scl/fi/j7m0gaz1126y594gswtma/CLEMMLST.pdf?rlkey=y5qvwq2er5nchbcibm07rcfpq&dl=0Clem and Matthew-https://www.linkedin.com/in/clement-bonnet16/https://github.com/clement-bonnethttps://mvmacfarlane.github.io/TOC1. LPN Fundamentals [00:00:00] 1.1 Introduction to ARC Benchmark and LPN Overview [00:05:05] 1.2 Neural Networks' Challenges with ARC and Program Synthesis [00:06:55] 1.3 Induction vs Transduction in Machine Learning2. LPN Architecture and Latent Space [00:11:50] 2.1 LPN Architecture and Latent Space Implementation [00:16:25] 2.2 LPN Latent Space Encoding and VAE Architecture [00:20:25] 2.3 Gradient-Based Search Training Strategy [00:23:39] 2.4 LPN Model Architecture and Implementation Details3. Implementation and Scaling [00:27:34] 3.1 Training Data Generation and re-ARC Framework [00:31:28] 3.2 Limitations of Latent Space and Multi-Thread Search [00:34:43] 3.3 Program Composition and Computational Graph Architecture4. Advanced Concepts and Future Directions [00:45:09] 4.1 AI Creativity and Program Synthesis Approaches [00:49:47] 4.2 Scaling and Interpretability in Latent Space ModelsREFS[00:00:05] ARC benchmark, Chollethttps://arxiv.org/abs/2412.04604[00:02:10] Latent Program Spaces, Bonnet, Macfarlanehttps://arxiv.org/abs/2411.08706[00:07:45] Kevin Ellis work on program generationhttps://www.cs.cornell.edu/~ellisk/[00:08:45] Induction vs transduction in abstract reasoning, Li et al.https://arxiv.org/abs/2411.02272[00:17:40] VAEs, Kingma, Wellinghttps://arxiv.org/abs/1312.6114[00:27:50] re-ARC, Hodelhttps://github.com/michaelhodel/re-arc[00:29:40] Grid size in ARC tasks, Chollethttps://github.com/fchollet/ARC-AGI[00:33:00] Critique of deep learning, Marcushttps://arxiv.org/vc/arxiv/papers/2002/2002.06177v1.pdf

  --------  

  51:26
• Prof. Jakob Foerster - ImageNet Moment for Reinforcement Learning?

  Prof. Jakob Foerster, a leading AI researcher at Oxford University and Meta, and Chris Lu, a researcher at OpenAI -- they explain how AI is moving beyond just mimicking human behaviour to creating truly intelligent agents that can learn and solve problems on their own. Foerster champions open-source AI for responsible, decentralised development. He addresses AI scaling, goal misalignment (Goodhart's Law), and the need for holistic alignment, offering a quick look at the future of AI and how to guide it.SPONSOR MESSAGES:***CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!https://centml.ai/pricing/Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich. Goto https://tufalabs.ai/***TRANSCRIPT/REFS:https://www.dropbox.com/scl/fi/yqjszhntfr00bhjh6t565/JAKOB.pdf?rlkey=scvny4bnwj8th42fjv8zsfu2y&dl=0 Prof. Jakob Foersterhttps://x.com/j_foersthttps://www.jakobfoerster.com/University of Oxford Profile: https://eng.ox.ac.uk/people/jakob-foerster/Chris Lu:https://chrislu.page/TOC1. GPU Acceleration and Training Infrastructure [00:00:00] 1.1 ARC Challenge Criticism and FLAIR Lab Overview [00:01:25] 1.2 GPU Acceleration and Hardware Lottery in RL [00:05:50] 1.3 Data Wall Challenges and Simulation-Based Solutions [00:08:40] 1.4 JAX Implementation and Technical Acceleration2. Learning Frameworks and Policy Optimization [00:14:18] 2.1 Evolution of RL Algorithms and Mirror Learning Framework [00:15:25] 2.2 Meta-Learning and Policy Optimization Algorithms [00:21:47] 2.3 Language Models and Benchmark Challenges [00:28:15] 2.4 Creativity and Meta-Learning in AI Systems3. Multi-Agent Systems and Decentralization [00:31:24] 3.1 Multi-Agent Systems and Emergent Intelligence [00:38:35] 3.2 Swarm Intelligence vs Monolithic AGI Systems [00:42:44] 3.3 Democratic Control and Decentralization of AI Development [00:46:14] 3.4 Open Source AI and Alignment Challenges [00:49:31] 3.5 Collaborative Models for AI DevelopmentREFS[[00:00:05] ARC Benchmark, Chollethttps://github.com/fchollet/ARC-AGI[00:03:05] DRL Doesn't Work, Irpanhttps://www.alexirpan.com/2018/02/14/rl-hard.html[00:05:55] AI Training Data, Data Provenance Initiativehttps://www.nytimes.com/2024/07/19/technology/ai-data-restrictions.html[00:06:10] JaxMARL, Foerster et al.https://arxiv.org/html/2311.10090v5[00:08:50] M-FOS, Lu et al.https://arxiv.org/abs/2205.01447[00:09:45] JAX Library, Google Researchhttps://github.com/jax-ml/jax[00:12:10] Kinetix, Mike and Michaelhttps://arxiv.org/abs/2410.23208[00:12:45] Genie 2, DeepMindhttps://deepmind.google/discover/blog/genie-2-a-large-scale-foundation-world-model/[00:14:42] Mirror Learning, Grudzien, Kuba et al.https://arxiv.org/abs/2208.01682[00:16:30] Discovered Policy Optimisation, Lu et al.https://arxiv.org/abs/2210.05639[00:24:10] Goodhart's Law, Goodharthttps://en.wikipedia.org/wiki/Goodhart%27s_law[00:25:15] LLM ARChitect, Franzen et al.https://github.com/da-fr/arc-prize-2024/blob/main/the_architects.pdf[00:28:55] AlphaGo, Silver et al.https://arxiv.org/pdf/1712.01815.pdf[00:30:10] Meta-learning, Lu, Towers, Foersterhttps://direct.mit.edu/isal/proceedings-pdf/isal2023/35/67/2354943/isal_a_00674.pdf[00:31:30] Emergence of Pragmatics, Yuan et al.https://arxiv.org/abs/2001.07752[00:34:30] AI Safety, Amodei et al.https://arxiv.org/abs/1606.06565[00:35:45] Intentional Stance, Dennetthttps://plato.stanford.edu/entries/ethics-ai/[00:39:25] Multi-Agent RL, Zhou et al.https://arxiv.org/pdf/2305.10091[00:41:00] Open Source Generative AI, Foerster et al.https://arxiv.org/abs/2405.08597<trunc, see PDF/YT>

  --------  

  53:31
• Daniel Franzen & Jan Disselhoff - ARC Prize 2024 winners

  Daniel Franzen and Jan Disselhoff, the "ARChitects" are the official winners of the ARC Prize 2024. Filmed at Tufa Labs in Zurich - they revealed how they achieved a remarkable 53.5% accuracy by creatively utilising large language models (LLMs) in new ways. Discover their innovative techniques, including depth-first search for token selection, test-time training, and a novel augmentation-based validation system. Their results were extremely surprising.SPONSOR MESSAGES:***CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!https://centml.ai/pricing/Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich.Goto https://tufalabs.ai/***Jan Disselhoffhttps://www.linkedin.com/in/jan-disselhoff-1423a2240/Daniel Franzenhttps://github.com/da-frARC Prize: http://arcprize.org/TRANSCRIPT AND BACKGROUND READING:https://www.dropbox.com/scl/fi/utkn2i1ma79fn6an4yvjw/ARCHitects.pdf?rlkey=67pe38mtss7oyhjk2ad0d2aza&dl=0TOC1. Solution Architecture and Strategy Overview[00:00:00] 1.1 Initial Solution Overview and Model Architecture[00:04:25] 1.2 LLM Capabilities and Dataset Approach[00:10:51] 1.3 Test-Time Training and Data Augmentation Strategies[00:14:08] 1.4 Sampling Methods and Search Implementation[00:17:52] 1.5 ARC vs Language Model Context Comparison2. LLM Search and Model Implementation[00:21:53] 2.1 LLM-Guided Search Approaches and Solution Validation[00:27:04] 2.2 Symmetry Augmentation and Model Architecture[00:30:11] 2.3 Model Intelligence Characteristics and Performance[00:37:23] 2.4 Tokenization and Numerical Processing Challenges3. Advanced Training and Optimization[00:45:15] 3.1 DFS Token Selection and Probability Thresholds[00:49:41] 3.2 Model Size and Fine-tuning Performance Trade-offs[00:53:07] 3.3 LoRA Implementation and Catastrophic Forgetting Prevention[00:56:10] 3.4 Training Infrastructure and Optimization Experiments[01:02:34] 3.5 Search Tree Analysis and Entropy Distribution PatternsREFS[00:01:05] Winning ARC 2024 solution using 12B param model, Franzen, Disselhoff, Hartmannhttps://github.com/da-fr/arc-prize-2024/blob/main/the_architects.pdf[00:03:40] Robustness of analogical reasoning in LLMs, Melanie Mitchellhttps://arxiv.org/html/2411.14215[00:07:50] Re-ARC dataset generator for ARC task variations, Michael Hodelhttps://github.com/michaelhodel/re-arc[00:15:00] Analysis of search methods in LLMs (greedy, beam, DFS), Chen et al.https://arxiv.org/html/2408.00724v2[00:16:55] Language model reachability space exploration, University of Torontohttps://www.youtube.com/watch?v=Bpgloy1dDn0[00:22:30] GPT-4 guided code solutions for ARC tasks, Ryan Greenblatthttps://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt[00:41:20] GPT tokenization approach for numbers, OpenAIhttps://platform.openai.com/docs/guides/text-generation/tokenizer-examples[00:46:25] DFS in AI search strategies, Russell & Norvighttps://www.amazon.com/Artificial-Intelligence-Modern-Approach-4th/dp/0134610997[00:53:10] Paper on catastrophic forgetting in neural networks, Kirkpatrick et al.https://www.pnas.org/doi/10.1073/pnas.1611835114[00:54:00] LoRA for efficient fine-tuning of LLMs, Hu et al.https://arxiv.org/abs/2106.09685[00:57:20] NVIDIA H100 Tensor Core GPU specs, NVIDIAhttps://developer.nvidia.com/blog/nvidia-hopper-architecture-in-depth/[01:04:55] Original MCTS in computer Go, Yifan Jinhttps://stanford.edu/~rezab/classes/cme323/S15/projects/montecarlo_search_tree_report.pdf

  --------  

  1:09:04
• Sepp Hochreiter - LSTM: The Comeback Story?

  Sepp Hochreiter, the inventor of LSTM (Long Short-Term Memory) networks – a foundational technology in AI. Sepp discusses his journey, the origins of LSTM, and why he believes his latest work, XLSTM, could be the next big thing in AI, particularly for applications like robotics and industrial simulation. He also shares his controversial perspective on Large Language Models (LLMs) and why reasoning is a critical missing piece in current AI systems.SPONSOR MESSAGES:***CentML offers competitive pricing for GenAI model deployment, with flexible options to suit a wide range of models, from small to large-scale deployments. Check out their super fast DeepSeek R1 hosting!https://centml.ai/pricing/Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich.Goto https://tufalabs.ai/***TRANSCRIPT AND BACKGROUND READING:https://www.dropbox.com/scl/fi/n1vzm79t3uuss8xyinxzo/SEPPH.pdf?rlkey=fp7gwaopjk17uyvgjxekxrh5v&dl=0Prof. Sepp Hochreiterhttps://www.nx-ai.com/https://x.com/hochreitersepphttps://scholar.google.at/citations?user=tvUH3WMAAAAJ&hl=enTOC:1. LLM Evolution and Reasoning Capabilities[00:00:00] 1.1 LLM Capabilities and Limitations Debate[00:03:16] 1.2 Program Generation and Reasoning in AI Systems[00:06:30] 1.3 Human vs AI Reasoning Comparison[00:09:59] 1.4 New Research Initiatives and Hybrid Approaches2. LSTM Technical Architecture[00:13:18] 2.1 LSTM Development History and Technical Background[00:20:38] 2.2 LSTM vs RNN Architecture and Computational Complexity[00:25:10] 2.3 xLSTM Architecture and Flash Attention Comparison[00:30:51] 2.4 Evolution of Gating Mechanisms from Sigmoid to Exponential3. Industrial Applications and Neuro-Symbolic AI[00:40:35] 3.1 Industrial Applications and Fixed Memory Advantages[00:42:31] 3.2 Neuro-Symbolic Integration and Pi AI Project[00:46:00] 3.3 Integration of Symbolic and Neural AI Approaches[00:51:29] 3.4 Evolution of AI Paradigms and System Thinking[00:54:55] 3.5 AI Reasoning and Human Intelligence Comparison[00:58:12] 3.6 NXAI Company and Industrial AI ApplicationsREFS:[00:00:15] Seminal LSTM paper establishing Hochreiter's expertise (Hochreiter & Schmidhuber)https://direct.mit.edu/neco/article-abstract/9/8/1735/6109/Long-Short-Term-Memory[00:04:20] Kolmogorov complexity and program composition limitations (Kolmogorov)https://link.springer.com/article/10.1007/BF02478259[00:07:10] Limitations of LLM mathematical reasoning and symbolic integration (Various Authors)https://www.arxiv.org/pdf/2502.03671[00:09:05] AlphaGo’s Move 37 demonstrating creative AI (Google DeepMind)https://deepmind.google/research/breakthroughs/alphago/[00:10:15] New AI research lab in Zurich for fundamental LLM research (Benjamin Crouzier)https://tufalabs.ai[00:19:40] Introduction of xLSTM with exponential gating (Beck, Hochreiter, et al.)https://arxiv.org/abs/2405.04517[00:22:55] FlashAttention: fast & memory-efficient attention (Tri Dao et al.)https://arxiv.org/abs/2205.14135[00:31:00] Historical use of sigmoid/tanh activation in 1990s (James A. McCaffrey)https://visualstudiomagazine.com/articles/2015/06/01/alternative-activation-functions.aspx[00:36:10] Mamba 2 state space model architecture (Albert Gu et al.)https://arxiv.org/abs/2312.00752[00:46:00] Austria’s Pi AI project integrating symbolic & neural AI (Hochreiter et al.)https://www.jku.at/en/institute-of-machine-learning/research/projects/[00:48:10] Neuro-symbolic integration challenges in language models (Diego Calanzone et al.)https://openreview.net/forum?id=7PGluppo4k[00:49:30] JKU Linz’s historical and neuro-symbolic research (Sepp Hochreiter)https://www.jku.at/en/news-events/news/detail/news/bilaterale-ki-projekt-unter-leitung-der-jku-erhaelt-fwf-cluster-of-excellence/YT: https://www.youtube.com/watch?v=8u2pW2zZLCs<truncated, see show notes/YT>

  --------  

  1:07:01

Meer Technologie podcasts

Trending Technologie -podcasts

Over Machine Learning Street Talk (MLST)