Alex Ebel

3D Artist by day - Creative Coder by night

[GameGPU @GameGPU_com]

https://t.co/XKjKtMvBwj

A technical glitch in neural rendering was documented in Grand Theft Auto V. While the game was paused, the internal engine stopped sending fresh frames to the presentation buffer.

Lacking a valid new frame, the model entered a recursive loop by constantly enhancing its own previous output. The blurred background was repeatedly scanned, which quickly distorted the character's face into chaotic visual artifacts.

This anomaly stems from a swapchain hook error that ignored the pause state. Generative models require precise engine integration and must shut down during static menu screens to prevent uncontrolled artifact generation.

#DLSS #Gaming #Graphics #TechNews #PCGaming #GameDev #Bugs

[Google AI @GoogleAI]

Our @GoogleResearch Connectomics team, in collaboration with @HHMIJanelia, has released the complete wiring diagram of a male fruit fly’s brain and central nervous system — the largest brain map by number of proofread neurons to date.

So, why do we care so much about a tiny fly's brain? 🧵👇

[Google AI @GoogleAI]

Oh, so this is why we mapped out all 166,000 of the male fruit fly's neurons. Check out the big community effort to show just how much these tiny fly brains are capable of 🪰🧵

[David Shapiro (L/0) @DaveShapi]

I was not fuckin ready for this 🤣

[Yudong Jin @krahets]

Single video in, 4D human out.

4DAnyone turns a casual monocular video into a 4DGS model.
No camera rig, no calibration, no tripod.

Project: https://t.co/hIArgF0YmQ

[Robert Scoble @Scobleizer]

I told you the future would be weird. 😜

[José M R P B @jmrpb772021]

Robert McGinnis y Frank McCarthy.
Cartel para "Operación Trueno", pintado en 1957.

[William Gilpin @wgilpin0]

Our group discovered that reasoning models produce fractals when asked to solve hard problems. We can use nonlinear dynamics to probe the thinking processes of recurrent depth models on Sudoku, mathematics, and even ARC-AGI (1/N)
https://t.co/Q3u8OqylZf

[Sebastian Aaltonen @SebAaltonen]

Game devs have wanted reflection and modules in C/C++ for decades. Nice simple code, no macro hacks, no constant include cleanups.

What we got instead —> :(

[Nekodificador 💬 @Nekodificador]

Denzel explica por qué usa la IA.

Un pequeña prueba explorando Minimax H3 en ComfyUI con mis nodos y métodos de inpainting.

[Sebastian Aaltonen @SebAaltonen]

NoGraphicsAPI is released (MIT license)!

It's a low-level Vulkan 1.4 wrapper using latest extensions (BDA, descriptor heap, device address commands, unified image layouts) to get as close as possibly to my No Graphics API blog post and SIGGRAPH 26 talk.

https://t.co/pnW5yRTkug

[David Pantera @davidpantera_]

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the @theworldlabs tech blog

Atlas is able to generate the parts of the scene that none of the cameras actually filmed.

It can freeze time, allowing you to reframe shots to positions never filmed, then resume.

View events from impossible angles because Atlas knows what was there.

[Justine Moore @venturetwins]

Re-shoot an existing video from a new angle 🤯

Truly insane work from @theworldlabs, this new model is a game-changer.

The initial clip was filmed with three cell phones on tripods - the model reconstructed a full view of the scene to reframe the video.

[Jon Barron @jon_barron]

Here's my talk from the CVPR 2026 "Bitter Lessons" workshop earlier this summer. I've split it up into parts for the sake of discussion.

Part 1: in which I wax poetic about my youth and force the audience to look at my dissertation results.

[Andrew Carr 🤸 @andrew_n_carr]

Most “physics from video” papers replay the clip or do some re-decode

LaGSplat learns a Lagrangian from a few seconds of monocular video, then lets you push on the object with a force that was never measured.

It's so neat that the same latent q drives the Gaussians and the equations of motion. That’s why a click on the image becomes J^f

https://t.co/ekonMFjGk4

[Hao Zhao @HaoZhao_AIRSUN]

🚨 A single image → a fully editable UE5 world.

Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians.

It gives you:
→ object-level 3D meshes
→ editable 3D layouts
→ engine-native lights
→ HDR environment lighting
→ a scene ready for Unreal Engine 5

In other words:
Image → 3D world → UE5.
We believe the future of image-to-3D is not “generate something that looks 3D.”

It is generate the actual world project.
🌐 https://t.co/SG87LXtZC8
📄 https://t.co/25od2QXRnf

[Toyojiro @Toyojiro3619]

久しぶりの回顧録。巨人に乗ってパルクールですが、やっている事は単純で、ワールドに動的配置された各ポイントに対して、距離や角度で評価して、最適と判断された位置にモーションワーピングで移動しているだけです。今回はデバッグ表示付きで。

#UnrealEngine5 #UE5 #GameDev #IndieDev #ゲーム制作

[Tav shande @artbytav]

I think I found a good way to make a tiling raindrop post process texture map never have the drops hit the same exact part of the screen. Fade the entire mask out after the first raindrop loop, pan the UVs a random amount and fade back in with a new x,y location.

[alexei @alexeixbt]

next time you think change isn't possible, this is an actual footage of the brain rewiring itself: