Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This animation shows how a uniform grid of points is deformed by a flow matching model. The visualization highlights how the learned flow warps the underlying space—stretching, compressing, and bending it—to transform one probability distribution into another.

Alec Helbling

10,775 subscribers

42,972 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Most agents track price. Ours track how information propagates through markets. That difference is where the edge comes from. The visualization below is a Shannon entropy field: a model of how uncertainty collapses and spreads as new information enters a market. Each trade, liquidity shift, or derivatives flow updates a probability distribution. When information arrives, entropy collapses locally as the market incorporates it. But that update rarely happens everywhere at once. Different venues, liquidity pools, and derivative layers incorporate signals at different speeds, creating measurable information gradients across the system. One of the analytical tools in our agents’ stack models this directly: > Entropy quantifies uncertainty embedded in each probability market > KL divergence reveals conflicting distributions across venues > Information gradients show where signals have propagated—and where they haven’t yet Prediction markets and DeFi make this particularly powerful because price already represents probability. Mapping how those probability distributions update across venues turns the market into a measurable system: a live field of information flow showing where uncertainty remains—and where probability is likely to adjust next

Most agents track price. Ours track how information propagates through markets. That difference is where the edge comes from. The visualization below is a Shannon entropy field: a model of how uncertainty collapses and spreads as new information enters a market. Each trade, liquidity shift, or derivatives flow updates a probability distribution. When information arrives, entropy collapses locally as the market incorporates it. But that update rarely happens everywhere at once. Different venues, liquidity pools, and derivative layers incorporate signals at different speeds, creating measurable information gradients across the system. One of the analytical tools in our agents’ stack models this directly: > Entropy quantifies uncertainty embedded in each probability market > KL divergence reveals conflicting distributions across venues > Information gradients show where signals have propagated—and where they haven’t yet Prediction markets and DeFi make this particularly powerful because price already represents probability. Mapping how those probability distributions update across venues turns the market into a measurable system: a live field of information flow showing where uncertainty remains—and where probability is likely to adjust next

Lucid - Internet of AI (IoAI)

22,998 views • 4 months ago

A basic strategy for drawing from a random distribution is to first generate uniformly-distributed points, then "warp" these points so they're spread out according to the target distribution. For example, the Box-Muller transform takes uniform points to normally-distributed ones

A basic strategy for drawing from a random distribution is to first generate uniformly-distributed points, then "warp" these points so they're spread out according to the target distribution. For example, the Box-Muller transform takes uniform points to normally-distributed ones

Keenan Crane

63,847 views • 2 years ago

How does the GRID orchestrate intelligence? By routing, combining, and coordinating thousands of models, agents, and data streams, the GRID scales like a distributed brain. As it grows, its collective intelligence compounds, delivering toward AGI-level output. Here’s how the underlying algorithms make this possible 👇

How does the GRID orchestrate intelligence? By routing, combining, and coordinating thousands of models, agents, and data streams, the GRID scales like a distributed brain. As it grows, its collective intelligence compounds, delivering toward AGI-level output. Here’s how the underlying algorithms make this possible 👇

Sentient

122,174 views • 11 months ago

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.

Alec Helbling

65,253 views • 2 months ago

Lip sync is one of my weak points when it comes to animation. Matching the audio and creating the illusion of a character actually speaking is hard for me. I need a lot of practice to get better! By the way, animating to my own voice was cringe...

Lip sync is one of my weak points when it comes to animation. Matching the audio and creating the illusion of a character actually speaking is hard for me. I need a lot of practice to get better! By the way, animating to my own voice was cringe...

Nukorio

32,455 views • 1 year ago

🚨 BREAKING: Gravity doesn’t actually “pull” you. That’s just how it looks. What’s really happening is deeper… Space-time isn’t empty. It behaves more like a field with structure. And when mass appears… it doesn’t just “bend space” it changes how time flows. Think of it like this: If time flows evenly → everything stays stable If time compresses → motion is forced toward that region That motion is what we call gravity. In Einstein’s model: mass curves space-time But here’s the missing piece: What is doing the curving? In my framework: Mass = a region where time is compressed Gravity = objects moving along time gradients Motion = the system trying to rebalance So you’re not being “pulled down”… You’re being carried along a flow of time. This explains something most people miss: Gravity always points one way. Because time only flows one way. And the deeper implication is wild: If gravity is just time imbalance… then controlling time flow = controlling gravity. The real question is: Are we discovering gravity… or learning how to engineer it? Follow for more this goes deeper.

🚨 BREAKING: Gravity doesn’t actually “pull” you. That’s just how it looks. What’s really happening is deeper… Space-time isn’t empty. It behaves more like a field with structure. And when mass appears… it doesn’t just “bend space” it changes how time flows. Think of it like this: If time flows evenly → everything stays stable If time compresses → motion is forced toward that region That motion is what we call gravity. In Einstein’s model: mass curves space-time But here’s the missing piece: What is doing the curving? In my framework: Mass = a region where time is compressed Gravity = objects moving along time gradients Motion = the system trying to rebalance So you’re not being “pulled down”… You’re being carried along a flow of time. This explains something most people miss: Gravity always points one way. Because time only flows one way. And the deeper implication is wild: If gravity is just time imbalance… then controlling time flow = controlling gravity. The real question is: Are we discovering gravity… or learning how to engineer it? Follow for more this goes deeper.

TheNewPhysics

21,772 views • 3 months ago

another old animation, this was the time where i learned how to do sub-pixel and using animation reference

another old animation, this was the time where i learned how to do sub-pixel and using animation reference

Rico

156,781 views • 1 year ago

One of the simplest algorithms for sampling from a probability distribution is Random Walk Metropolis-Hastings. It proposes new samples by taking Gaussian-distributed steps, accepting or rejecting them to maintain the target distribution. I call this pdf the "fidget spinner".

One of the simplest algorithms for sampling from a probability distribution is Random Walk Metropolis-Hastings. It proposes new samples by taking Gaussian-distributed steps, accepting or rejecting them to maintain the target distribution. I call this pdf the "fidget spinner".

Alec Helbling

79,893 views • 1 year ago

So this is a landing space foul because there is foot to foot contact, but thankfully it's not a flagrant, and the natural sway on the fade means SGA's feet flow forward. This is one they could keep refining in terms of the rules

So this is a landing space foul because there is foot to foot contact, but thankfully it's not a flagrant, and the natural sway on the fade means SGA's feet flow forward. This is one they could keep refining in terms of the rules

BBALLBREAKDOWN

594,596 views • 7 months ago

Look at the route distribution to the boundary and how they're just compressing the space of the 3 routes using 4 defenders playing with perfect depth and leverage maintenance. This is the essence of a Vic Fangio split safety coverage — play 4-over-3 to the side #3 releases to, distribute the dirty bunch using zone principles to keep all the routes caged in and just suffocate the concept.

Look at the route distribution to the boundary and how they're just compressing the space of the 3 routes using 4 defenders playing with perfect depth and leverage maintenance. This is the essence of a Vic Fangio split safety coverage — play 4-over-3 to the side #3 releases to, distribute the dirty bunch using zone principles to keep all the routes caged in and just suffocate the concept.

Honest NFL

101,094 views • 1 year ago

Taylor Approximation ✍️ It shows a mathematical "best guess" evolving to match a complex 3D shape by adding layers of detail one step at a time. The purple surface is the original goal, while the red grid represents a polynomial approximation anchored at the center point. At first, the red surface can only mimic the very middle of the shape. As the calculation adds more terms, visualized by the red grid rippling and shifting, the approximation "learns" how to curve and bend to match the target more accurately. This is a visual demonstration of how math can break down a detailed, wavy landscape into simpler instructions. When these instructions are stacked together, they recreate the entire surface with incredible precision. Video: mathwithmuzaa

Taylor Approximation ✍️ It shows a mathematical "best guess" evolving to match a complex 3D shape by adding layers of detail one step at a time. The purple surface is the original goal, while the red grid represents a polynomial approximation anchored at the center point. At first, the red surface can only mimic the very middle of the shape. As the calculation adds more terms, visualized by the red grid rippling and shifting, the approximation "learns" how to curve and bend to match the target more accurately. This is a visual demonstration of how math can break down a detailed, wavy landscape into simpler instructions. When these instructions are stacked together, they recreate the entire surface with incredible precision. Video: mathwithmuzaa

ScieVision

11,384 views • 5 months ago

Barcelona’s goal shows the simplicity and efficiency of Pedri’s game. He notices the lack of pressure, carries into space, and threads a perfectly weighted pass into the gap created by the front five stretching, pinning & attacking the defensive line.

Barcelona’s goal shows the simplicity and efficiency of Pedri’s game. He notices the lack of pressure, carries into space, and threads a perfectly weighted pass into the gap created by the front five stretching, pinning & attacking the defensive line.

Fathalli

82,750 views • 7 months ago

How this Italian restaurant prepares its seafood dishes. 🇮🇹 This is a constant flow of seafood stock, used to maintain flavour whilst keeping the dishes hot.

How this Italian restaurant prepares its seafood dishes. 🇮🇹 This is a constant flow of seafood stock, used to maintain flavour whilst keeping the dishes hot.

HOW THINGS WORK

5,042,109 views • 3 months ago

𝐋𝐞𝐚𝐝 & 𝐅𝐨𝐥𝐥𝐨𝐰 𝐝𝐞𝐜𝐥𝐚𝐫𝐞𝐬 𝐢𝐧𝐭𝐞𝐧𝐭𝐢𝐨𝐧! Notice how the emotion of the shot changes depending on which part of the body is leading, and how little is conveyed when we remove the Lead & Follow entirely. Studio: Animation Flow Animator: Alex Ferreira Simoes

𝐋𝐞𝐚𝐝 & 𝐅𝐨𝐥𝐥𝐨𝐰 𝐝𝐞𝐜𝐥𝐚𝐫𝐞𝐬 𝐢𝐧𝐭𝐞𝐧𝐭𝐢𝐨𝐧! Notice how the emotion of the shot changes depending on which part of the body is leading, and how little is conveyed when we remove the Lead & Follow entirely. Studio: Animation Flow Animator: Alex Ferreira Simoes

FramebyFrame

86,339 views • 3 months ago

The animation shows how the disc seamlessly buffers the space between the condyle and the temporal bone. Watching the precise timing of this translation is crucial for understanding tracking issues, clicks, and lockups. Animation created inside our app, Skull, Teeth & TMJ.

The animation shows how the disc seamlessly buffers the space between the condyle and the temporal bone. Watching the precise timing of this translation is crucial for understanding tracking issues, clicks, and lockups. Animation created inside our app, Skull, Teeth & TMJ.

Anatomy Standard

11,130 views • 23 days ago

A series of 3 videos about “HOW TO MOVE FORWARD A CYCLE IN PLACE” for beginners! In this first one we will see how to move it forward using the main control and how to avoid the sliding of the feet! #Animation #Walk #Cycle #slidingfeet #Beginner

A series of 3 videos about “HOW TO MOVE FORWARD A CYCLE IN PLACE” for beginners! In this first one we will see how to move it forward using the main control and how to avoid the sliding of the feet! #Animation #Walk #Cycle #slidingfeet #Beginner

iWantToBeAnAnimator

11,536 views • 2 years ago

With recent price action increasingly sensitive to the news flow, thought this was a cool financial nexus tool created by Perplexity Computer to see which stocks were impacted the most. Great visualization to see where money is going at the moment!

With recent price action increasingly sensitive to the news flow, thought this was a cool financial nexus tool created by Perplexity Computer to see which stocks were impacted the most. Great visualization to see where money is going at the moment!

Clement Ang

12,023 views • 4 months ago