Diffusion models leverage a variety of samplers. Deterministic methods... like DDIM produce orderly paths. In contrast, stochastic samplers like DDPM produce chaotic trajectories. Despite their differences, both methods draw valid samples from the underlying distribution.show more

Stochastic and deterministic sampling strategies for diffusion models produce... strikingly different trajectories, but both ultimately achieve the same aim. I had a great time presenting our work, Diffusion Explorer, this week at IEEE VIS in Vienna.show more

Create a 3D model from a single image, set... of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”show more

Outfits are cool... but what about hairstyles? AIKODE offers... a wide variety of hairstyles with custom physics that work seamlessly in both cutscenes and gameplay. You can change the color, add different tint masks and accessories. Each hairstyle is fully rigged, strand by strand, ensuring that every style (despite significant differences) functions just like the default hair, without any glitches in cutscenes or gameplay. Here you can see some of the hairstyles in-game. #aikode #UE5show more

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper... page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.show more

Disney's new research on neural rendering really upped the... game. They start by path tracing and then running light gathering on those paths. Then they train a little network, kinda like a NERF, to produce those lighting results directly. It essentially keeps the lighting team from requiring a full (complex) re-render every-time they move a light. But it keeps the lighting team fully in the driver's seat creatively. Definitely a great use of AI for advanced storytelling and animation.show more

🚨Exciting news for archaeology and for human knowledge in... general! It has been a long and tedious process, but the Peruvian Ministry of Culture has finally granted permission to export geological samples that will hopefully enable the age of Sacsayhuaman's construction to be determined! Three types of samples have been collected for analysis using different dating methods, and some of them are already on their way to different labs in the US and in Europe. 1 - Soil samples collected from right beneath the blocks that make up the megalithic walls of Sacsayhuaman for Optically Stimulated Luminescence (OSL) dating – this method is used to determine the time elapsed since minerals like quartz and feldspar were last exposed to sunlight by measuring the light energy (luminescence) released from trapped electrons that accumulated in the mineral crystal lattice due to natural radiation since their last bleaching/reset event (i.e., when the ground was covered by the blocks). 2 - Limestone samples from megalithic blocks, quarry sites and carved bedrock, for Cosmogenic Nuclides dating – this method is used to determine the age of geological surfaces by measuring the accumulation of rare isotopes (mainly ³⁶Cl) produced when the limestone is hit by cosmic rays. 3 - Speleothems samples (calcium carbonate deposits such as stalactite or flowstone) collected on carved surfaces for Uranium-Thorium dating – this method is used to calculate the age of carbonate materials by measuring the buildup of thorium-230 from the slow decay of its uranium-234 parent isotope. This won’t give us the age of the carving of these rocks, but this will give us a minimum age, since the rock was obviously cut before these deposits formed. Additionally, if some organic material is found in the soil or speleothems samples, radiocarbon dating will also be performed, which would give us a fourth means of dating the construction of the site. Whether you believe this megalithic site was built by the Incas or by a much older civilization, science will hopefully put an end to this debate once and for all. And, to top it all off, some limestone samples have also been sent to the Geopolymer Institute of Joseph Davidovits for analysis. This is proof, if any were needed, that not all archaeologists are dogmatic and closed to alternative theories. Now, Let's hope that all these methods will yield results. Whatever these results may be, they will be the subject of a scientific publication, and I will share them here on X, so make sure to follow. This could potentially rewrite history!show more

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from... In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.show more

Just like yesterday when we introduced the use of... a hoist machine for casting the upper floors (around the 3rd and 4th floors), Sammyrex could remember, some of the casters who worked on the 1st and 2nd floors complained that we were wasting money. They said they had been carrying concrete on their heads from ground floor up to the 8th–10th floors for over 10 years. But instead of seeing it as unnecessary spending, they should see it as progress, because in some projects, concrete pumps are even used. Construction should move with safer, faster, and more efficient methods.show more

As a graphics engine coder I think when you... look at a flickering bug like this one in the video below it’s not immediately obvious what is going on. The key here is observation - to study this flickering/bugged render carefully - what do we see? Firstly for me it was very obvious that nearly all of the scene shadows were flashing on and off - but (but!) there was a secondary issue where some buildings and parts of the sky were also flashing purple. Hmmmm. Interesting. I initially thought then this might be two separate bugs - but because the sky purple element could only based on full screen post fx and not 3D rendering I looked at this first with a few GPU captures to step through all our post processing to find the rendering stage which made these pixels turn purple: When I did this I found the colour 3D texture LUT grading that makes our different biomes have unique colour palettes was going very wrong - colours near 0 or 1 were wrapping and making the purple elements that we see in the said sky and base parts. The only way this could happen was if the texture was corrupt (which it was not) or if the 3D texture sampling was wrapping and not clamped as intended. That was the Eureka moment - because if the post fx had the wrong texture sampler then the disappearing shadows which also require an exact texture sampler for comparing depth might be also wrong because of the same kind of texture sampling issue! So with this idea that the engine was using the wrong texture samplers, but only in very high draw call scenes like the big base here I the looked at some engine limits and found the bug very quickly - a circular dx12 descriptor buffer for samplers running out over multiple frames, reusing the wrong data for new scenes inflight. Hence the flickering, as the GPU randomly got wrong samplers for some post textures or shadow depth. Easy to fix with triple limits for future expansion and also adding an assert/debug spam in case this limit is ever reached again - QA testers would see this message and report if they ever saw a flicker with this style of bug. My bug and my bad from 2017 porting NMS to DX12 without foreseeing how massively complex bases and our game would grow.show more

🌀 #Live3D #Live2D #Live2DWIP 🌀 Today, I’d like to... share two of the three methods I use to create joint twisting in my Live2D-based 2D Pseudo-3D concept. On the right is the Glue Joint： The basic idea is to use Glue to connect two pseudo-3D ArtMeshes. By taking advantage of Glue’s weight settings, it can create an effect similar to a 3D joint. Once the weights are set up, it can move very freely with a relatively low amount of work. However, it also shares the same weakness as 3D joints: when rotated at large angles, it can produce unpleasant twisting and distortion. On the left is the Hand-Bent Joint： The basic idea is to add bending Keyforms directly to a Warp Deformer, then manually sculpt the ideal deformation. This method can create the most detailed and refined joints, depending entirely on how the rigger designs them. The downside is that it requires much more work. Every additional degree of freedom requires a significant amount of manual adjustment. These two joint methods have almost opposite characteristics, so in actual Live3D work, I choose the most suitable method depending on the situation. For example, in this hand model, I used Hand-Bent Joints for the arm twisting and fingers, while the wrist uses a Glue Joint.✨show more

We've donated over 13,000 dollars to National Children's Advocacy... Center going towards preventing sexual and physical abuse of children. What started as a simple meme evolved into something beautiful thanks to this comment: It's because of you we were able to donate life changing money to support children in a time where epstein's crimes are not being prosecuted. I got to speak with the woman on the phone and learn a small part of her story and understand where the funds are going. NCAC is the FIRST child support centre in the world, and the money is being used for both current trauma support, and preventative methods with 0 cost to the victims or their family. It's all funded by donations, like ours. Our token address: 7p8hs6fZwTXvSYESCdHgWCXVsVcxTrX1cs3Q4yNGpumpshow more

The new argument they’re trying to push about Suwayda,... the mountainous extension of the highly fertile Hawran region, is that it is supposedly an entirely barren area with no viable agriculture whatsoever. It is an amusing claim, considering that (1) much of the region’s population historically depended on agriculture (and many still do, despite declining rainfall in recent years having severely affected local farmers), and (2) large parts of the region look like what you see in the video below. Then I suddenly remembered that one of the first complaints surrounding the impasse between the new authorities in Damascus and the local authorities in Suwayda, well before the massacres, came from local farmers demanding a resolution so they could resume exporting their produce outside the province. I looked into it further and came across this report by Sham TV from February 2025: apparently, farmers in Suwayda were complaining that they had 17,000 tons (yes, you read that correctly!) of apples stored in cold storage facilities, with no clear way to sell or export them because of the ongoing impasse. So much for an entirely barren region, after all… 🤦‍♂️ P.S. There are many reasons why a landlocked region with a relatively small population like Suwayda may not be viable as an independent state. The absence of viable agriculture is simply not one of them.show more

The AI hunt for alien life has just begun.... Welcome to ThousandsWorlds, a wild new dataset from researchers at Oxford/Cambridge++, for detecting faint signatures in the atmospheres of potentially habitable exoplanets. This is the first step towards finding life beyond earth. The plan is basically: 1) scan the galaxy for as many potentially habitable planets as possible 2) detect the gases in their atmospheres with powerful telescopes like JWST 3) infer from these gases whether life is present or not. ThousandWorlds is a benchmark for emulating these exoplanet climates: 1760 simulations across 5 GCMs, 8 planet parameters, and atmospheric variables on a 32 x 64 x 10 latitude-longitude-pressure grid. It includes three nested benchmark subsets, two evaluation protocols, and eight released baseline methods. incredible work from Miles Cranmer and many more 👽👽👽show more

How many sandwiches can you help provide today? Donate... here: Every day, The Sameer Project kitchen is working to keep families fed in conditions where access to food is still extremely limited. The daily operational cost is around $8,500-$9,000 - covering ingredients, cooking, packaging, and distribution so meals can reach those who are hungry and malnourished. Each sandwich costs less than $3 to prepare and distribute - like the kofta sandwiches you see here! A full day at capacity can produce 3,000 sandwiches to be given out to hungry families in need of assistance. Even a small contribution is a meal for a child, a parent, and elder, someone who didn’t know where their next food would come from. To donate is to help keep the kitchen running…give to our Food and Water Campaign: Other ways to donate include: (Paypal option, please make sure to add a message saying "Food") (Venmo option, please make sure to add a message saying "Food")show more

WATCH THIS VIDEO CAREFULLY. FORENSIC ANALYSIS OF A VIDEO... CURRENTLY BEING CIRCULATED AND SPREAD ON ARAB TELEGRAM CHANNELS (Mor Edge Insight in conjunction with GAZAWOOD - The Pallywood Saga - BACKUP - July 6) What you are about to see is raw footage of an active arrest operation and genuine footage. This clip is currently circulating on Palestinian Telegram channels and is being prepared for wider distribution on X. It follows a familiar pattern of real footage with heavy manipulation and inauthentic audio to create a perception and narrative that doesn’t exist and is not what the footage actually shows. Here is the step-by-step forensic breakdown. The audio track contains multiple sharp “gunshots.” However, frame-by-frame examination shows no muzzle flashes at any point, even in bright daylight where unsuppressed firearms would produce clear, visible bursts. There is also no visible recoil or weapon movement on the individuals holding rifles. The barrels show no suppressors, yet the sounds are relatively clean “pops” rather than the overwhelming cracks expected from unsuppressed fire at that range. The audio of the shots fired are more reminiscent of a children’s toy than a real gunshot. More critically, the visual action is happening at a clear distance across the road, at a distance of an estimated 60-100m away from the camera, yet the gunshots and shouting sound as if recorded right next to the camera. Real distant gunfire would be thinner, more muffled, and accompanied by environmental echoes. This audio was added in post-production. How distance was determined: The white car in the immediate foreground (partially visible on the left) is only 5–10 meters away. The road width and the position of the parked vehicles and people with guns put the core action clearly in the mid-ground, across the full width of the street and shoulder. Reference objects: Standard car lengths (4.5–5m), average adult height (1.7m), and the spacing of streetlights/power poles all support a distance in that 60–100 meter range for the shooters and the SUV. The black SUV drives a noticeable distance across the frame without appearing overly large or close, further confirming it’s not right next to the camera. This distance makes the audio mismatch even more obvious. Real gunfire at 60–100 meters would sound significantly more distant and muted, with clear delay and environmental filtering. The overlaid “cracks” sound like they were recorded (or synthesized) much closer. Summary 1. Real gunshots, especially in an open outdoor environment like this, produce a sharp initial crack (supersonic bullet) followed by a broader report/echo, with significant low-frequency rumble, reverberation off the ground/cars/objects, and environmental decay. These sound more like clean “pop/crack” samples layered on top. 2. They lack the natural variations in volume, timing, or distortion you’d expect from actual firearms in a real chaotic scene (muzzle blast, echoes, distance differences) even with silencers which from that distance you wouldn’t even hear. They feel “pasted in” during editing. 3. The overall audio mix (ambient road noise, car sounds, voices) doesn’t interact naturally with the “shots”, there is no proper masking, reverb bleed, or mic overload you’d get from real loud events captured on the same recording device. Always examine the audio against the visuals, check for continuity errors, and watch how people actually behave when they think no one is watching the performance. Share if you value this kind of detailed verification.show more

Zelensky is systematically sabotaging Trump’s peace plan An assassination... attempt has been carried out in Moscow against Vladimir Alexeyev, Deputy Chief of Russia’s military intelligence (GRU). Alexeyev has been hospitalized and is reported to be in serious condition. There is nothing unusual about what is happening. Zelensky continues to act using methods that reflect escalation and destabilization. It is particularly telling that such events occur precisely during so-called negotiations which could theoretically produce results — if their primary point were Zelensky’s removal from power. As long as this does not happen, escalation will continue and any real prospects for a genuine peace process will be undermined. This is yet another terrorist act. Moreover, it represents another blow to the efforts of Donald Trump and other political actors attempting to build a path toward peace. While some are trying to create space for dialogue, Zelensky consistently destroys any real prospects for negotiations.show more

This is insane Ubisoft.. After spending over 200 hours... with Assassin’s Creed Shadows, I can confidently say it is a masterpiece. Having played numerous AAA titles, I can attest that this stands among the best ever created. The level of detail is astounding—from the breathtaking landscapes and stunning artistry to the deep, engaging combat system and the intricate stealth mechanics. The sheer variety of ways to execute assassinations is remarkable. I keep telling my friend @AbiAkano that I can’t believe this is a Ubisoft game. First, they delivered Prince of Persia: The Lost Crown, which I absolutely loved and felt it deserved far more recognition. Now, they’ve released what I consider their best game in years—an achievement that truly leaves me in awe. The passion and dedication from the developers are evident in every aspect of this game. It’s moments like these that remind me why I love gaming—despite the occasional frustrations that come with it.show more