[[2412.01276] Shadow of the (Hierarchical) Tree: Reconciling Symbolic and Predictive Components of the Neural Code for Syntax](https://arxiv.org/abs/2412.01276) [[2410.13166] An Evolved Universal Transformer Memory](https://arxiv.org/abs/2410.13166) https://fxtwitter.com/SakanaAILabs/status/1866286131685498920?t=BnOxECG53IjwbSdBZwrTcg&s=19 Gradient descent x evolution [[1810.06773] Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks](https://arxiv.org/abs/1810.06773) [Adapting to time: Why nature may have evolved a diverse set of neurons | PLOS Computational Biology](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012673) [Neural Turing machine - Wikipedia](https://en.wikipedia.org/wiki/Neural_Turing_machine) [Differentiable neural computer - Wikipedia](https://en.wikipedia.org/wiki/Differentiable_neural_computer) deepseek https://x.com/reach_vb/status/1872000205954089011 o1 [https://www.youtube.com/watch?v=6PEJ96k1kiw](https://www.youtube.com/watch?v=6PEJ96k1kiw) [https://youtu.be/rJkTsNrnu8g?si=rXA27hRIV5gkVHiD](https://youtu.be/rJkTsNrnu8g?si=rXA27hRIV5gkVHiD) [https://www.youtube.com/watch?v=AfAmwIP2ntY](https://www.youtube.com/watch?v=AfAmwIP2ntY) https://fxtwitter.com/gm8xx8/status/1871814856904478798?t=9c0HsVIk_VQbAQQyTI8XZA&s=19 [[2412.18319] Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search](https://arxiv.org/abs/2412.18319) https://fxtwitter.com/gm8xx8/status/1871644052166418867?t=YNarMXqmUbhm7sEm_taDkQ&s=19 [[2412.17256] B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners](https://arxiv.org/abs/2412.17256) Kenneth Stanley [Kenneth Stanley - Wikipedia](https://en.wikipedia.org/wiki/Kenneth_Stanley) [[2501.04682] Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://arxiv.org/abs/2501.04682) [[2412.06769] Training Large Language Models to Reason in a Continuous Latent Space](https://arxiv.org/abs/2412.06769) https://x.com/NovaSkyAI/status/1877793041957933347 [Sky-T1: Train your own O1 preview model within $450](https://novasky-ai.github.io/posts/sky-t1/) [[2501.04519] rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://arxiv.org/abs/2501.04519) https://x.com/ziv_ravid/status/1877736408191754487 [[2501.05707] Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://arxiv.org/abs/2501.05707) [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://llm-multiagent-ft.github.io/) https://x.com/du_yilun/status/1878851914307371440 Transformer^2 [[2501.06252] Transformer-Squared: Self-adaptive LLMs](https://arxiv.org/abs/2501.06252) Cognitive agent architecture for multiagent AI civilizations: "PIANO" (Parallel Information Aggregation via Neural Orchestration) that "enables agents to interact with humans and other agents in real-time while maintaining coherence across multiple output streams" in Minecraft [[2411.00114] Project Sid: Many-agent simulations toward AI civilization](https://arxiv.org/abs/2411.00114) https://x.com/GuangyuRobert/status/1852397383939960926 inference time scaling of diffusion models https://fxtwitter.com/iScienceLuvr/status/1879094413588107319 [[2501.06848] A General Framework for Inference-time Scaling and Steering of Diffusion Models](https://arxiv.org/abs/2501.06848) "Our experimental results on language modeling, common-sense reasoning, genomics, and time series tasks show that Titans are more effective than Transformers and recent modern linear recurrent models." https://fxtwitter.com/behrouz_ali/status/1878859086227255347 [[2501.00663v1] Titans: Learning to Memorize at Test Time](https://arxiv.org/abs/2501.00663v1) Wake up babe new transformer killer dropped [[2501.07301] The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://arxiv.org/abs/2501.07301) It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces. [[2501.07542] Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://arxiv.org/abs/2501.07542) [[2206.07682] Emergent Abilities of Large Language Models](https://arxiv.org/abs/2206.07682) [[2301.08028] A Survey of Meta-Reinforcement Learning](https://arxiv.org/abs/2301.08028) >supervised fine-tuning (SFT) helps the model memorize and align with certain outputs, while reinforcement learning (RL) helps the model generalize and learn out-of-distribution (OOD) tasks SFT to tame initial instruction following, and then RL to generalize [[2501.17161] SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://arxiv.org/abs/2501.17161) https://x.com/Hesamation/status/1884579088121073972 [[2411.13420] Heuristically Adaptive Diffusion-Model Evolutionary Strategy](https://arxiv.org/abs/2411.13420) https://x.com/edwardfhughes/status/1887492625453793471?t=bXqO9PkNQOO_rgcbhCjGFw&s=19 Self play self driving I predict that reasoning in latent space will be the next set of breakthroughs Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach [[2502.05171] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://arxiv.org/abs/2502.05171) [[2502.05078] Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures](https://arxiv.org/abs/2502.05078) https://x.com/burny_tech/status/1890189798494941691 [Variational Bayes Gaussian Splatting: A Bayesian Approach for Continual 3D Learning](https://www.verses.ai/research-blog/variational-bayes-gaussian-splatting-a-bayesian-approach-for-continual-3d-learning) [Variational Bayes Gaussian Splatting](https://arxiv.org/html/2410.03592v1) https://fxtwitter.com/DimitrisPapail/status/1889755872642970039?t=Vr-9NWmA1IG51D_LJzhA2Q&s=19 [[2502.01612] Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges](https://arxiv.org/abs/2502.01612) https://fxtwitter.com/omarsar0/status/1889681118913577345 [[2502.06049] LM2: Large Memory Models](https://arxiv.org/abs/2502.06049) memory-augmented Transformer architecture that incorporates a dynamic memory module large memory models reasoning papers https://fxtwitter.com/TheAITimeline/status/1888720075793793121?t=6pLwpwpjNBhPr2zJP96dLA&s=19 New Levin paper [[2411.13420] Heuristically Adaptive Diffusion-Model Evolutionary Strategy](https://arxiv.org/abs/2411.13420) wordcels vs latentspacerotators https://x.com/burny_tech/status/1890194390066594120 [[2502.05171] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://arxiv.org/abs/2502.05171) https://x.com/takeru_miyato/status/1893538672533733601 [Artificial Kuramoto Oscillatory Neurons](https://takerum.github.io/akorn_project_page/) Artificial Kuramoto Oscillatory Neurons uses Kuramoto model which is also used in computational neuroscience [Neural oscillation - Wikipedia](https://en.wikipedia.org/wiki/Neural_oscillation#Kuramoto_model) [[2502.17543] Training a Generally Curious Agent](https://arxiv.org/abs/2502.17543) [[2502.21321] LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://arxiv.org/abs/2502.21321) [[2502.09992] Large Language Diffusion Models](https://arxiv.org/abs/2502.09992) [ARC-AGI Without Pretraining | iliao2345](https://iliao2345.github.io/blog_posts/arc_agi_without_pretraining/arc_agi_without_pretraining.html) - Transformers (Attention) - RNNs (LSTMs, GRUs) - [CNNs](https://arxiv.org/abs/1810.13118) - GNNs / KGs - Manifold-based learning (UMAP, t-SNE, autoencoders (VAEs)) - Spectral-based models (Fourier Neural Operators (FNOs)) - Mamba (SSMs) - Memory-Augmented NNs (NTMs, DNCs) - Energy-based & Variational models (EBMs) - KANs - Flow-based models (CNFs) - GANs - Diffusion models and Stable Diffusion - Liquid NNs / SNNs " "However, real scientific breakthroughs will come not from answering known questions, but from asking challenging new questions and questioning common conceptions and previous ideas. We're currently building very obedient students, not revolutionaries. This is perfect for today’s main goal in the field of creating great assistants and overly compliant helpers. But until we find a way to incentivize them to question their knowledge and propose ideas that potentially go against past training data, they won't give us scientific revolutions yet. If we want scientific breakthroughs, we should probably explore how we’re currently measuring the performance of AI models and move to a measure of knowledge and reasoning able to test if scientific AI models can for instance: Challenge their own training data knowledge Take bold counterfactual approaches Make general proposals based on tiny hints Ask non-obvious questions that lead to new research paths We don't need an A+ student who can answer every question with general knowledge. We need a B student who sees and questions what everyone else missed. https://x.com/Thom_Wolf/status/1897630495527104932 " [[2410.01131] nGPT: Normalized Transformer with Representation Learning on the Hypersphere](https://arxiv.org/abs/2410.01131) [[2211.01233] Attention-based Neural Cellular Automata](https://arxiv.org/abs/2211.01233) enhanced knowledge graphs and reasoning LLMs [[2502.13025] Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks](https://arxiv.org/abs/2502.13025) [https://youtu.be/W2uauk2bFjs?si=MVhlTpK2kbaxmt-a](https://youtu.be/W2uauk2bFjs?si=MVhlTpK2kbaxmt-a) neural celluar automata [Growing Neural Cellular Automata](https://distill.pub/2020/growing-ca/) [Differentiable Logic CA: from Game of Life to Pattern Generation](https://google-research.github.io/self-organising-systems/difflogic-ca/) [Cortical - CL1](https://corticallabs.com/cl1.html) it's the people connected to Friston who are behind the paper where they taught biological neurons to ping ping where they mention the free energy principle [In vitro neurons learn and exhibit sentience when embodied in a simulated gameworld | by Cortical Labs | Medium](https://corticallabs.medium.com/in-vitro-neurons-learn-and-exhibit-sentience-when-embodied-in-a-simulated-gameworld-387ec3f2c870) [[2502.06034] Traveling Waves Integrate Spatial Information Through Time](https://arxiv.org/abs/2502.06034) "Traveling Waves Integrate Spatial Information Through Time In the physical world, almost all information is transmitted through traveling waves -- why should it be any different in your neural network? Just as ripples in water carry information across a pond, traveling waves of activity in the brain have long been hypothesized to carry information from one region of cortex to another; but how can a neural network actually leverage this information? This paper introduces convolutional recurrent neural networks that learn to produce traveling waves in their hidden states in response to visual stimuli, enabling spatial integration. They made wave dynamics flexible by adding learned damping and natural frequency encoders, allowing hidden state dynamics to adapt based on the input stimulus. By then treating these wave-like activation sequences as visual representations themselves, they obtain a powerful representational space that outperforms local feed-forward networks on tasks requiring global spatial context. In particular, they observe that traveling waves effectively expand the receptive field of locally connected neurons, supporting long-range encoding and communication of information. They demonstrate that models equipped with this mechanism solve visual semantic segmentation tasks demanding global integration, significantly outperforming local feed-forward models and rivaling non-local U-Net models with fewer parameters. Video shows Tetris-like dataset and variants of MNIST to compare the semantic segmentation ability of these wave-based models with two relevant baselines: Deep CNNs w/ large receptive fields, and small U-Nets." [[2408.08435] Automated Design of Agentic Systems](https://arxiv.org/abs/2408.08435) automating factorio https://fxtwitter.com/bio_bootloader/status/1899147299546423507 [Factorio Learning Environment](https://jackhopkins.github.io/factorio-learning-environment/) https://x.com/renxyzinc/status/1899539629411270758 [8 Universal State Machine – Infinite Time Turing Machines and their Applications](https://opensource.getren.xyz/ittm/8_usm.html) Universal state machine >dynamically growing symbolic graphs Reminds me of [[2502.13025] Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks](https://arxiv.org/abs/2502.13025) [https://youtu.be/W2uauk2bFjs?si=MVhlTpK2kbaxmt-a](https://youtu.be/W2uauk2bFjs?si=MVhlTpK2kbaxmt-a) Abandoning Objectives: Evolution through the Search for Novelty Alone [https://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/lehman_ecj11.pdf](https://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/lehman_ecj11.pdf) Why Greatness Cannot Be Planned [Why Greatness Cannot Be Planned: The Myth of the Objective | SpringerLink](https://link.springer.com/book/10.1007/978-3-319-15524-1) #72 Prof. KEN STANLEY 2.0 - On Art and Subjectivity [UNPLUGGED] [https://www.youtube.com/watch?v=DxBZORM9F-8](https://www.youtube.com/watch?v=DxBZORM9F-8) https://x.com/burny_tech/status/1894491541227671779 " Kenneth Stanley is my spirit animal rage against the predefined objectives embrace the fully divergent search full of novelty and accidental epiphany with serendipity [https://www.youtube.com/watch?v=DxBZORM9F-8](https://www.youtube.com/watch?v=DxBZORM9F-8) [https://www.youtube.com/watch?v=_2vx4Mfmw-w](https://www.youtube.com/watch?v=_2vx4Mfmw-w) it's an evolutionary breeding process of images, but humans pick the images that should have offsprings idea: picbreeder but let multimodal LLMs instead of humans choose the next image in the evolutionary breeding process 🤔 [https://www.youtube.com/watch?v=_2vx4Mfmw-w](https://www.youtube.com/watch?v=_2vx4Mfmw-w) i need to look more into how those novelty/diversity algorithms that he's mentioning work, maybe they can be added into RL reward functions in LLM RL https://www.researchgate.net/publication/46424802_Abandoning_Objectives_Evolution_Through_the_Search_for_Novelty_Alone New research project: Lluminate - an evolutionary algorithm that helps LLMs break free from generating predictable, similar outputs. Combining evolutionary principles with creative thinking strategies can illuminate the space of possibilities. https://x.com/_joelsimon/status/1899884376172982392?t=Z4q0CZ2C5-9v8A-QJPnpNA&s=19 [https://www.joelsimon.net/lluminate](https://www.joelsimon.net/lluminate) Metagradient Descent [[2503.13751] Optimizing ML Training with Metagradient Descent](https://arxiv.org/abs/2503.13751) https://x.com/f14bertolotti/status/1902259983753842971 [Chain-of-Draft (CoD) Is The New King Of Prompting Techniques](https://intoai.pub/p/chain-of-draft-cod-is-the-new-king) [[2502.18600] Chain of Draft: Thinking Faster by Writing Less](https://arxiv.org/abs/2502.18600) https://x.com/METR_Evals/status/1902384481111322929?t=4SbjaExBNAyL4W-3w881lQ&s=19 [[2503.14499] Measuring AI Ability to Complete Long Tasks](https://arxiv.org/abs/2503.14499) [[2202.09467] Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?](https://arxiv.org/abs/2202.09467) [https://www.youtube.com/watch?v=48GRiu-TMmg](https://www.youtube.com/watch?v=48GRiu-TMmg) https://fxtwitter.com/ericzhao28/status/1901704339229732874?t=fJDIBbvCb2b_QIBxnsHiLw&s=19 [[2502.01839] Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://arxiv.org/abs/2502.01839) https://x.com/eric_haibin_lin/status/1901662955307200974 https://x.com/Synced_Global/status/1901794723633025282?t=pIRCz8vUZxj92QQ9aMrBzg&s=19 [https://dapo-sia.github.io/static/pdf/dapo_paper.pdf](https://dapo-sia.github.io/static/pdf/dapo_paper.pdf) DAPO algorithm grpo uphrade [https://www.youtube.com/watch?v=4KK2NjMrcjo](https://www.youtube.com/watch?v=4KK2NjMrcjo) [[2503.24322] NoProp: Training Neural Networks without Back-propagation or Forward-propagation](https://arxiv.org/abs/2503.24322) [https://www.youtube.com/watch?v=UMkCmOTX5Ow](https://www.youtube.com/watch?v=UMkCmOTX5Ow) An Evolved Universal Transformer Memory [Paper] [[2410.13166] An Evolved Universal Transformer Memory](https://arxiv.org/abs/2410.13166) Memory Layers at Scale [Paper] [[2412.09764] Memory Layers at Scale](https://arxiv.org/abs/2412.09764) Titans: Learning to Memorize at Test Time [Paper] [[2501.00663] Titans: Learning to Memorize at Test Time](https://arxiv.org/abs/2501.00663) [https://www.youtube.com/watch?v=qhYQ20TbtJ8](https://www.youtube.com/watch?v=qhYQ20TbtJ8) CoCoNuT: Training Large Language Models to Reason in a Continuous Latent Space [Paper] [[2412.06769] Training Large Language Models to Reason in a Continuous Latent Space](https://arxiv.org/abs/2412.06769) Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach [Paper] [[2502.05171] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://arxiv.org/abs/2502.05171)