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.

interpolating image embeddings across arbitrary numbers of vertices. using polygons as lenses through n-dimensional latent space.

harley turan

13,019 subscribers

23,036 views • 10 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

exploring paths through latent space by interpolating between known embeddings

exploring paths through latent space by interpolating between known embeddings

harley turan

96,332 views • 10 months ago

Agents can now understand physical space and temporality on Dimensional. Input: “Find the model airplane” With SpatioTemporal RAG, our agent has an emergent understanding of objects, stairwells, and obstacles in latent space.

Agents can now understand physical space and temporality on Dimensional. Input: “Find the model airplane” With SpatioTemporal RAG, our agent has an emergent understanding of objects, stairwells, and obstacles in latent space.

stash

10,485 views • 5 months ago

[1/n] Do distinct large models admit a simple map that aligns their embedding spaces? We show that across multimodal contrastive models—trained on different data and architectures—an orthogonal map aligns image embeddings. Strikingly, the same map also aligns text embeddings.

[1/n] Do distinct large models admit a simple map that aligns their embedding spaces? We show that across multimodal contrastive models—trained on different data and architectures—an orthogonal map aligns image embeddings. Strikingly, the same map also aligns text embeddings.

Sharut Gupta

37,180 views • 4 months ago

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming

Wildminder

27,210 views • 1 month ago

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Wildminder

15,679 views • 2 months ago

Shadows of The Shining Exploring the latent space of The Shining is to approach the film as one approaches a memory. Here, artificial intelligence acts as a second consciousness: it does not reproduce — it remembers. It reconstructs The Shining from its traces, its echoes, from what has survived the narrative. The latent space becomes a mental territory, an inner Overlook where the ghosts of the image, the logic of dreams, and the mechanisms of visual memory unfold once again. The aim is to turn the exploration of the latent space into a mnemonic experience of cinema itself.

Shadows of The Shining Exploring the latent space of The Shining is to approach the film as one approaches a memory. Here, artificial intelligence acts as a second consciousness: it does not reproduce — it remembers. It reconstructs The Shining from its traces, its echoes, from what has survived the narrative. The latent space becomes a mental territory, an inner Overlook where the ghosts of the image, the logic of dreams, and the mechanisms of visual memory unfold once again. The aim is to turn the exploration of the latent space into a mnemonic experience of cinema itself.

Benjamin Bardou

37,491 views • 8 months ago

A CNN is a tiny grid of numbers dragged across an image. Multiply, add, squash.

A CNN is a tiny grid of numbers dragged across an image. Multiply, add, squash.

tetsuo

11,248 views • 1 month ago

Extremely proud of our recent "Lost in Latent Space" paper by our amazing PolymathicAI intern François Rozet ! How far do you think we can/should compress ? What is needed in the latent space to keep rolling out the physics right across so many scales?

Extremely proud of our recent "Lost in Latent Space" paper by our amazing PolymathicAI intern François Rozet ! How far do you think we can/should compress ? What is needed in the latent space to keep rolling out the physics right across so many scales?

Shirley Ho

51,275 views • 10 months ago

New work with Yide Shentu! We present Latent Code as Bridges🌉 or LCB. We leverage LLMs for robotics by finetuning the LLM to output latent embeddings to control the lower level policy. This hierarchical approach enables end2end training while maintaining the advantages of LLMs!

New work with Yide Shentu! We present Latent Code as Bridges🌉 or LCB. We leverage LLMs for robotics by finetuning the LLM to output latent embeddings to control the lower level policy. This hierarchical approach enables end2end training while maintaining the advantages of LLMs!

Philipp Wu

21,072 views • 2 years ago

"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer" TL;DR: learns a continuous mesh latent space and generates vertices and connectivity in parallel with flow matching, producing quality 3D meshes up to 18× faster than autoregressive.

"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer" TL;DR: learns a continuous mesh latent space and generates vertices and connectivity in parallel with flow matching, producing quality 3D meshes up to 18× faster than autoregressive.

Alexandre Morgand

43,016 views • 26 days ago

Raising a little garden from latent space On M2 Max, using SD 1.5, ControlNet, TripoSR, and three.js. Sped up for brevity.

Raising a little garden from latent space On M2 Max, using SD 1.5, ControlNet, TripoSR, and three.js. Sped up for brevity.

Evan Jones

109,852 views • 2 years ago

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

stash

228,249 views • 2 months ago

ColPali is changing the game for PDF retrieval by eliminating the need for OCR and chunking methods 🚀 Inspired by ColBERT’s success with text, ColPali splits an image of a document into patches, which are then processed through a vision LLM called PaliGemma. The embeddings for each patch retain contextual information, similarly to text embeddings in methods like ColBERT. During retrieval, user queries are embedded in the same space, and then compared to document patches using the MaxSim operator. ColPali recipe POC Weaviate AI Database: ColPali paper: As always, shoutout to the awesome Daniel Williams for the help! 💙

ColPali is changing the game for PDF retrieval by eliminating the need for OCR and chunking methods 🚀 Inspired by ColBERT’s success with text, ColPali splits an image of a document into patches, which are then processed through a vision LLM called PaliGemma. The embeddings for each patch retain contextual information, similarly to text embeddings in methods like ColBERT. During retrieval, user queries are embedded in the same space, and then compared to document patches using the MaxSim operator. ColPali recipe POC Weaviate AI Database: ColPali paper: As always, shoutout to the awesome Daniel Williams for the help! 💙

Victoria Slocum

67,833 views • 1 year ago

I'm releasing a new latent space explorer 🧭🎨 — a creative tool for generating and evolving images. It's tree-based and designed for creative flow and open-ended discovery, using image mixing, branching, and editing. You can try it out now on ArtBreeder!

I'm releasing a new latent space explorer 🧭🎨 — a creative tool for generating and evolving images. It's tree-based and designed for creative flow and open-ended discovery, using image mixing, branching, and editing. You can try it out now on ArtBreeder!

Joel Simon

19,874 views • 1 year ago

POV: you are a being of pure entropy living in GPT-5 latent space

POV: you are a being of pure entropy living in GPT-5 latent space

Beff (e/acc)

44,395 views • 2 years ago

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,142 views • 2 years ago

A fan that produces a three-dimensional holographic image

A fan that produces a three-dimensional holographic image

OpenMoon

1,219,812 views • 2 years ago

To recreate the look of late-1960s Hollywood, Once Upon a Time in Hollywood (2019) was shot using vintage Panavision anamorphic lenses, giving the film its characteristic flares and softer, more organic image.

To recreate the look of late-1960s Hollywood, Once Upon a Time in Hollywood (2019) was shot using vintage Panavision anamorphic lenses, giving the film its characteristic flares and softer, more organic image.

Best Movie Moments 🍿

20,104 views • 3 months ago

Europa League qualification: Through the lenses of the admin 👓📱

Europa League qualification: Through the lenses of the admin 👓📱

Sunderland AFC

26,231 views • 1 month ago