Déda et al. use neural networks for flow analysis... & control in nonlinear fluid systems, showcasing accuracy & stabilization in complex dynamics. From the Lorenz system to confined cylinder flows, neural networks shine as effective models & controllers.show more

Do you have experience in microscopy, image analysis, fluid... dynamics, network theory, electrophysiology, and/or machine learning? Join us as we track the flows & structure of mycorrhizal networks. We have a biophysics post-doc position open in Amsterdamshow more

SuiRWA is training its investment AI agents on extensive... data, using neural networks for pattern recognition. They learn via supervised & unsupervised methods, with fine-tuning for market analysis, ensuring accuracy and minimizing bias. A revolution in investing might be here.show more

In nature, researchers from Google Quantum AI, TU München,... & UoN Physics & Astronomy simulated a (2+1)D lattice gauge theory and visualized string dynamics, revealing the deconfined-to-confined excitation transition as the effective electric field increases. →show more

The theory of higher order topological dynamics, which combines... multilevel interactions between discrete topology and nonlinear dynamics, has the potential to enhance our understanding of complex systems such as the functions of the nervous system, the development of next-generation machine learning and the creation of advanced nodal processing algorithms. An important and unexpected collective behavior of signal processing in multilevel nodal networks has been observed to lead to a synchronization and diffusion of the irrotational and the solenoidal components of the systems revealing a deep relation of these mechanisms with the complexity of discrete topology. The perspective of the preliminary study linked here offers insights into how topology morphs dynamics, how dynamics stem from topology and how topology evolves dynamically. 🔗show more

#SfN23 Come to WCC 147A at 2pm tomorrow to... hear my talk on the neural basis of cuttlefish camouflage✨ Even better, come to the whole session (1-3pm) for neuroethology of sensorimotor systems in spiders, hydra, bats, octopus & more! 🕷️🐙🦇🐒 @SFNtweetsshow more

It's been incredible to see neural networks working so... well on our humanoid robots Humanoids are crazy complex - an individual motor can rotate 360 degrees and you have 40+ joints. If you do the math, that means more possible robot states than atoms in the universe Figure has our own AI model called Helix that we've designed in-house. A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input Every leap in machine learning has come from massive, diverse datasets. At Figure, we’re currently building the largest pretraining dataset for humanoids in history - excited to see what this unlocksshow more

Thrilled to share UniRig from Tripo Tripo VAST AI... Research: an AI model for rapid automatic 3D rigging. Rig diverse models—from humans, animals, to sci-fi creatures—in seconds! UniRig has the potential to streamline animation workflows with unparalleled accuracy & versatility.show more

🚨🇷🇺🇨🇳 Russia and China develop breakthrough AI-powered earthquake forecasting... method The new AI model predicts earthquakes by tracking changes in the Earth’s crust with superior accuracy—at a fraction of traditional computing costs. 🔸 Geoacoustic emissions are used — sounds produced as tectonic stress builds up underground — to pinpoint possible earthquake precursors 🔸The new system combines Physics-Informed Neural Networks (PINNs) with Kolmogorov-Arnold Networks (KANs) to process seismic data 🔸 The team proposes using human-made noise as seismic sonar to reveal underground details that natural signals miss 🔸 The approach slashes computing costs while delivering sharper 2D and 3D geological maps Beyond earthquake forecasting, the same technology could also aid mineral exploration and infrastructure planning—by revealing subsurface structures with unprecedented clarityshow more

Here are more results from #RigidFormer: predicting physical dynamics... with purely neural simulators — an attempt to learn physical dynamics in a scalable manner. 🤖 1) Controllable Articulated Body Simulation — More Results Additional Unitree G1 humanoid rollouts under controlled motion. Each sample uses a different initial state and control signal (direction and velocity). 🏺 2) Object Fragmentation Simulating the cracking and fragmentation process of objects. Thanks Žiga Kovačič for suggesting this experiment! 🎬 3) Combining Rigidformer with Diffusion-as-Shader for controllable video generation. Note: the meshes shown here are only for visualization — the network takes point clouds as input and predicts the updated state of each point.show more

Columbo couldnt say no to Kos' big ol puppy... eyes! Just a short I got the idea to do that features my chosen voice actors for em! Tom Kenny as Kosmo & Peter Falk as Peter Fox/Columbo! 🔊is from SpongeBob "Squid Noir" & The In-Laws(1979)! ...Surprised I didnt use Columbo audio? xDshow more

Predicting the next word "only" is sufficient for language... models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.show more

🇨🇳🇺🇸 China's military may be learning from America's AI,... without building it from scratch Why spend billions training a frontier AI model when you can let someone else do the expensive part? Chinese military-linked researchers have repeatedly used outputs from OpenAI and Anthropic models to train smaller domestic AI systems for surveillance, cyber operations, drone targeting, battlefield decision-making, and software analysis. The trick is called distillation: instead of copying the model itself, researchers use its answers, and more importantly, its reasoning, to teach a smaller model. The result? AI that isn't as powerful as the original, but is cheap, runs on local hardware, and can be deployed on drones, military networks, and tactical systems without relying on U.S technology. The AI arms race isn't just about who builds the smartest model anymore; it's about who can squeeze the most military value out of everyone else's. Source: Reuters / Writer: Ianshow more

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction... Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."show more

🚨 SCIENTISTS ARE USING AI TO MAP A HIDDEN... “CLEANING SYSTEM” INSIDE THE HUMAN BRAIN AND IT COULD CHANGE HOW WE UNDERSTAND SLEEP, AGING, AND NEURODEGENERATIVE DISEASE. It’s called the glymphatic system a vast network of fluid channels that flushes toxic waste from the brain while you sleep. For years it was almost impossible to observe in detail. Now AI-powered imaging is revealing it like a living galaxy of microscopic rivers and pathways inside neural tissue. Why this matters: Your brain produces toxic proteins constantly. The glymphatic system is one of its primary waste-clearance mechanisms clearing the very proteins linked to Alzheimer’s, Parkinson’s, and other neurodegenerative diseases. But here’s the unsettling part: This cleaning system becomes dramatically less efficient with age, poor sleep, stress, and brain injury. Sleep may not just “rest” your mind it may literally wash your brain. The deeper implication is staggering: The brain isn’t just a computer. It’s a dynamic, living network that constantly rebuilds and cleanses itself in real time. The more we map it, the more it looks like an entire universe of connected energy flows inside our skulls. What if some neurological diseases begin when the brain can no longer properly “wash” itself at night? Follow for more frontier neuroscience and future technology.show more

Biomni Lab lets biologists collaborate with AI agents to... finish complex tasks end-to-end. Here are 15 popular use cases, each link is a full replay so you can watch the agent work through every step: 1. Spatial transcriptomics analysis: map gene expression across tissue architecture from spatial transcriptomics data, with spatial clustering and neighborhood analysis. 2. Binder design: design de novo protein binders against a target structure using computational protein design tools. 3. Biomarker panel design: identify and optimize a multi-marker diagnostic or prognostic panel from omics data. 4. Clinical trial landscaping: search and summarize the trial landscape for a disease area, mapping phase, endpoints, and sponsor activity. 5. Survival analysis: pull clinical and expression data, fit Cox models, generate Kaplan-Meier curves, and identify prognostic markers. 6. scRNA-seq processing and annotation: from raw counts to UMAP clustering, marker gene detection, and automated cell type labeling. 7. Cell-cell communication: infer ligand-receptor interactions between cell types from single-cell data and map intercellular signaling networks. 8. Primer design for novel Cas13: analyze a putative Cas13 protein from a metagenomic screen—verify the ORF, identify HEPN domains, and design cloning primers with restriction sites and a FLAG 9. Proteomics differential expression: normalize mass spec data, run statistical tests, and visualize differentially abundant proteins. 10. Gene regulatory network inference: reconstruct transcription factor-target gene networks from expression data and identify key regulators. 11. Gene co-expression network analysis: build weighted co-expression networks, identify gene modules, and correlate them with phenotypic traits. 12. Microbiome analysis: process 16S/metagenomic sequencing data to profile microbial communities, diversity, and differential abundance. 13. Polygenic risk scores: compute and evaluate PRS from GWAS summary statistics against a target cohort. 14. Variant annotation: annotate genetic variants with functional predictions, allele frequencies, and clinical significance. 15. Fine-mapping: narrow GWAS loci to credible causal variants using statistical fine-mapping methods. Each of these would normally take days to weeks of scripting, debugging, and iteration. In Biomni Lab, the agent handles the full execution while you steer the science. Learn more:show more

Do you ever wonder what happens inside the mind... of an elite athlete? I absolutely love this perspective from gold medal freeskier Eileen Gu on the power of our mindset and belief system: "You can control how you think. And therefore, you can control who you are." Athletes don’t just magically create routines and habits. They’re supported by coaches who use the principles of behavioral science to set them up for success. That means using techniques to reduce decision fatigue and lower stress. Through neuroplasticity, the small choices we repeat every day can strengthen our neural circuits and rewire our brains to make certain behaviors more automatic, which is exactly what Gu has trained her mind to do. As Gu said, “With neuroplasticity on my side, I can become exactly who I want to be.” What was your favorite moment of the Winter 2026 Olympics? Let me know in the comments!show more

I believe the "Pit" described in the book of... Revelation is a Galactic Federation prison deep under Antarctica, where "Satan" and "Lucifer" are already confined. From Pleiadian contact we know that the primary leader of the dark forces on Earth is a reptilian with four arms named Pidkozox. He's from the planet Uranus (Nebulac) in our solar system, but in a different dimension. Pidkozox is the father of two Sirian sons, Ashtar and Oppisheklio. Elder Ashtar is the leader of Sirius, a close friend to Elder Ikai, and a respected Galactic Federation commander. Oppisheklio is Earth's greatest deceiver, who played Good Cop to his father's Bad Cop. They were known by many names, including Enlil and Enki, Zeus and Apollo, Baal and Yahweh. They can't harm us directly and rely on human free will to carry out their plans. In blood rituals, they give commands to elites, who then control networks of puppets worldwide. We're in a system with oversight by Galactic Federation which allows dark forces to deceive us without harming us directly, and allows humans to harm each other with free will. Until the Shift, we're dealing with dark plans carried out by humans, as well as spiritual warfare, but we don't have to worry about physical encounters with negative extraterrestrials or defeating the dark forces.show more

🇷🇺 Russia’s Starlink killers showcase new era of electronic... battlefield warfare Russia has ramped-up EW use to detect and jam Elon Musk’s Starlink terminals and satellites, Ukrainian media reports. 👉 Meet Russia’s key counter-Starlink systems: 🔸 Volna Kupol Garant Russia’s latest electronic warfare system reportedly uses a directed high-frequency radio beam to disrupt Starlink operations. Rather than damaging satellites orbiting roughly 500 kilometers above Earth, the system blinds them – cutting their ability to connect with ground terminals while they remain under attack. According to reports, Volna is a mobile system built around six trailers. Each carries a pair of steerable satellite dishes mounted on rotating platforms. A single battery is reportedly capable of denying Starlink coverage across an area of up to 20 sq km. Some analysts say the system was previously referenced under the designation Peresvet-M, although this has not been independently confirmed. Ukrainian sources claim Volna was first deployed during Russia's offensive in the Kharkov region in 2024. They also say its use has increased significantly in recent months. 🔸 Tobol The secretive Russian EW complex is reportedly used to disrupt signals from NATO-linked satellite networks, including GPS, Galileo, and Starlink. Reports claim that Tobol attacks satellite communications on both ends of the link – jamming downlinks from satellites to ground receivers and uplinks from Earth to orbit. Its power and range also allegedly allow it to create an electromagnetic "umbrella." 🔸 Kalinka The system is designed to hunt down satellite communications signals, including those transmitted by Starlink terminals at distances of up to 15 km. It can reportedly track and lock onto even Starshield – SpaceX’s hardened military variant of Starlink. Western media warns that while Tobol disrupts GPS signals on a broad scale, the Kalinka’s precision-targeting capabilities could pose a more direct threat to specific military operations. 🔸 Krasukha The Krasukha-S4 is designed to neutralize reconnaissance satellites, ground-based radar installations, and airborne surveillance systems. It does so by emitting powerful electronic jamming signals that disrupt key radar bands and other radio-frequency emissions. A standard Krasukha-S4 battery consists of two vehicles and has an operational range exceeding 300 kilometers. 🔸 Borshchevik The light mobile system is designed to detect and geolocate Starlink terminals within a 180-degree sector at ranges of up to 10 km, with a reported accuracy of five meters. Using direction-finding and biangulation algorithms, it can locate a target in less than three minutes at a single scanning position. The Borshchevik-2 airborne system hunts Starlink signals from the sky, with reported accuracy down to 0.4 m.show more

Model-Free Reinforcement Learning (MFRL) has been alluring, especially with... supercharged compute with physics on GPU. However, the methods use 0-th order gradients, and are often not the best optimizers. Can we do better than PPO in continuous control for robotics? Turns out yes! 🥳 tl;dr: Faster, better RL than PPO in continuous control 💪 The answer lies in using more information from the simulation. We are juicing the simulation on GPU as it is, why not use it for gradients as well? This has been a driving question in a series of our works. We first studied this problem in ICLR 2022 paper on Short Horizon Actor Critic Naive gradient based methods are stuck in local minima and have exploding/vanishing gradients. SHAC solved this problem truncated rollouts and model based value estimation, where the model is Differentiable Sim. This boosted sample efficiency and wall-clock time immensely especially in high dimensional systems such as humanoids Yet, given enough compute PPO often caught up. Our follow up paper on on Adaptive Horizon Actor Critic at ICML 2024 discovers the cause and provides a fix. However, we find that even when given ground-truth dynamics, not all gradients are useful due to sample error. 1st-Order Model-Based Reinforcement Learning methods employing differentiable simulation provide gradients with reduced variance but are susceptible to bias in scenarios involving stiff dynamics, such as physical contact. We find that back-propagating through contact and long trajectories drastically reduces gradient accuracy. Using this insight, we propose AHAC to dynamically adapt its roll-out horizon to avoid differentiating through stiff contact. AHAC is a first-order model-based RL algorithm that learns high-dimensional tasks in minutes (wall clock) and outperforms PPO by 40%, even in the limit of data provided to PPO. This work is led by Ignat Georgiev alongside Krishnan Srinivasan, Jie Xu, Eric Heiden and ample assistance from warp team at NVIDIA Robotics (Miles Macklin)show more