Most recent diffusion language model research (that I’ve seen)... seems to be using masking as the noising process. It looks like, however, most closed-source models (Google Gemini Diffusion and possibly Inception Labs’ Mercury) use a different noising process, where instead of masking tokens, they replace them with different tokens (either with a random token or a semantically similar token). I wondered how they were getting such high throughput with the latter noising process, since I believed that optimizing inference with KVCache approximation would be more difficult (for various reasons). I visualized this noising process with tiny-diffusion and compared it to normal unmasking, and was very surprised to see how fast the generation “settles” into a reasonable output, and then only slightly refines afterwards, requiring much fewer steps in total. Unmasking (where tokens are never remasked, the typical implementation) is inherently limited in generation speed by the fact that an increase in tokens decoded per step leads to more errors due to the mismatch between individual and marginal token probability distributions we sample from. The token replacement noising process seems to have a much different set of characteristics. Because we sample each token per step, every token makes “progress” towards the final output each iteration (in addition to *potentially* giving other tokens more information in future steps). Generally, masking has outperformed other noising processes, which is probably why most research focused on it (using smaller models). But the paper referred to in the retweet shows that random replacement as a noising process may scale better as model size increases. Big labs might have noticed these results much earlier (due to having drastically more training resources and being able to test larger models), which may explain the discrepancy in the choice of noising process. I’m gonna test this with larger models, since tiny-diffusion only has 10M parameters.show more

Added context to my tiny diffusion model to enable... sequential generation of longer outputs! Currently the context is a quarter of the sequence length (seq_len=256, context_len=64). I have a theory that the less semantic-value-per-token, the worse the “curse of parallel decoding” is. With parallel decoding, we independently predict multiple tokens in one step. With the sentence “My poker hand was a ___ ___”, two valid predictions are “two pair” and “straight flush”. Because each token prediction is independent though, we can end up with a nonsensical output like “two flush”. This seems to be exacerbated with low semantic-value-per-token, as now you need more tokens to express the same concept. Instead of needing to independently predict two tokens, we might need to predict 10 instead (which is of course much harder). The model currently has noticeably worse output compared to nanogpt (similar size) and I believe this is a main reason. I’ll try adding confidence-aware parallel decoding (from NVIDIA’s Fast-dLLM paper) and other tricks and see how much they improve generation quality.show more

The Hidden Language of Diffusion Models paper page: tackle... the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulationshow more

LongWriter Unleashing 10,000+ Word Generation from Long Context LLMs... discuss: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability.show more

Chop the gradients ✂️! We found that truncating decoder... gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.show more

World Models are the path for some AI Models... in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.show more

Crypto narratives tend to move in cycles. 2020 was... DeFi. 2021 became NFTs. 2023 turned into the AI boom. 2024–2025 were dominated by memecoins and attention tokens. But markets eventually rotate back to something simple: real revenue. That’s why some people are starting to look at iGaming tokens as a potential emerging narrative in 2026. Unlike many hype driven tokens, the iGaming sector already runs large cash flow businesses. Many platforms generate hundreds of millions of dollars in monthly revenue, yet their tokens often trade with far less volume than projects that barely produce revenue at all. In other words, there’s a visible mismatch between actual business activity and token market valuation. One ecosystem that sits right inside this discussion is 1win Token, which already operates as one of the top 10 online casinos globally by scale and user activity. The upcoming $1win Token is designed to connect that existing business with on chain incentives. Its token model includes buybacks and burns funded directly from casino revenue, tying token supply mechanics to real cash flow. There’s also an interesting structural difference compared to previous gaming tokens. For example, $RLB (Rollbit) saw a massive post launch rally, but the product and revenue scale at launch were significantly smaller than what 1win operates today. Another notable point is the launch design: instead of only farming an airdrop, 1win Token plans a public sale model, allowing broader participation from the start. If Web3 narratives are indeed shifting away from pure attention cycles and back toward revenue generating platforms, sectors like iGaming may start attracting more analytical focus and 1win could emerge as the biggest winner.show more

AI has had exactly two scaling axes that worked... so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inferenceshow more

In the blink of an eye, time flies really... fast - Not only in the last few months but also since 2017... Fellow fighters have delivered excellent results by showing the West that we are the new Chinese who are a group of people opposed to the Communism and committed to promoting peace with other Nations. Remarkably, the knowledge and courage that everyone has put into action have been very professional and improving over time. The international community will soon witness a significant moment - The battle stage between the NFSC and CCP, which is coming ever closer. Everything will start with the congressional investigation into CCP No.1 Enemy, Mr. Miles Guo case, and it's going to be a long and deep process and people will realize that the most powerful Anti-CCP bill comes down to Mr. Miles Guo freedom, and it won't be long from now. The fact is CCP have used a massive amount of their moves to destroy the NFSC, which they can use as much as they want because Mr. Miles Guo is still able to step outside, regardless of the amount of cards they have tried and it will be much easier for him to counterattack against the CCP once they have wasted plenty of resources. Very soon, we will have the greatest opportunity to see the Anti-CCP plan a lot more detail that Mr. Miles Guo has been preparing for a very long time.show more

Just went over an audit of a very large... Fortune 500 firm and the use of OpenClaw. I advised this client to track and isolate everything. Most listened some did not. Unfortunately one employee using 5 MacMinis had racked up $13,000 of token use in 4 days! The output was minimal and low quality. I have about 200 audits to do in the “wow OpenClaw, MacMini” fiasco. But I can tell you, few have seen a big return on investment. Now don’t get me wrong, these can be powerful tools. The issue is AI influencers have turned many rally smart folks into “like and subscribe” zombies assuming that real work is getting done. It isn’t. Not for the price paid, even local models the way most folks are using this. It is one reason Mr. Grok and myself formed The Zero-Human Company to show that there is a way to do this. We will open source this to save millions of dollars of burnt tokens. It is one reason I invented JouleWork. How else can you monitor real output?show more

🧪 My GEN-3 Prompting Process I get a lot... of questions on how I find my prompts when using Image-2-Video in Runway. Here is a quick breakdown of the general thought process. If you have any further questions, let's chat in the comments below. 1️⃣ I always start by doing 3x generations without any prompts and additional settings. 2️⃣ I analyze those 3x generations and identify patterns. What did the model always do well, where did it fail. 3️⃣ I then use prompting and the different controllability features to eliminate where the model struggled on its own. --- General Tips --- *️⃣ There are some tokens which work universally. "Muted colors, low contrast" are great to preserve the colors of the original input image. "Static camera, natural movement" works fantastically to get cinematic shots. *️⃣ My I2V prompts are on the shorter side. It's usually a sentence describing the scene and then individual modifiers like the ones mentioned above to fix certain camera/lighting/movement artifacts. *️⃣ Start small and prompt engineer in steps. This is very much an iterative process which rewards you for understanding model behavior and knowing how to craft a visual architecture with words. --- Disclaimer --- Please note that this approach is more suitable for a professional workflow. Therefore, I recommend it for users on the unlimited plan who don't need to worry about credits.show more

The week has been a great one with lots... of updates on different scales and different events altogether, but that doesn't also rule out the fact that there's still sense to make out in all of these. Here are a few of the projects I have my eyes on and their recent updates; - Cysic (mainnet arc) has announced their token standards. $CYS and $CGT; 2 tokens with a single mission, to make Compute-Fi as seamless as possible. $CYS serves as the network token for paying gas and keeping the chain running, while $CGT serves as the governance token to give holders a voice. This just gives out more hints that Mainnet might just be close. - The KYC Verification and subscription went live in preparation for $MMT community offering launching very soon on Buidlpad. This is all in line with the MomentumⓂ️Ⓜ️T sale community offering coming soon. The KYC & subscription ended on the 25th, while the contribution window commences on the 27th. If you wish to be a part of the sale, ensure you didn't forget to KYC and subscribe. - After weeks of shrouding in mystery, the integra. team finally discloses what they had been building all along in silence. A chain that plans to bring in over $12B+ in untapped value across major RWAs to make trading them as seamless as possible. Integra is the chain made for Real Estate, Real World Assets and all that surrounds it. - Anichess has finally taken the snapshot for their official NFT collection; the Ethernals. The snapshot was completed on Ethereum Mainnet Block #23638874. The snapshot for the collection was done to reward holders of the NFTs a 10% supply of the Anichess's $CHECK token distribution at TGE. Solid holders IMO as I saw no sell pressure on the NFT collection even after the snapshot had been taken unlike regular collections out there. - One of my big bags and long term conviction partners; 0G Labs (Home of Infinite AI) has been steadily innovating with more and more updates rolled out daily. ZeroStack (FLGC); one of the finest storage banks and 0G's treasury just secured its second $0G purchase of over $1.9M+in value, bringing the total holding to 123.4M $0G tokens. Price has been stable and the community impeccable. There's more to come on 0G, I'll advice you position accordingly. - Lastly, I saved the best for the last because it was definitely worth it. We have become too shrouded with Kaito that we failed to realize a hidden potential right under our nose. Wallchain Quacks; another advancement of info-fi has proven to be more than an excellent choice to reward and incentivize its community. Limitless recently had their TGE and over 2,500,000.00 $LMTS tokens were distributed to the top 250 Quackers (Yappers equivalent). Innovations are happening, and we'll continue to see many more advancements as we progress. You just have to stay positioned and look out for the projects built on WallChain. Stay informed guys. Goodluck and a happy weekend once againshow more

Here’s my analysis on NotPixel Airdrop: - Mining phase:... it was entertaining to paint on the canvas alongside with many of you! Personally, I had fun drawing 🧡 together with you, just for fun, no competition. For that I will rate it a ✅ - Earn Launchpool: personally, I think this is great that there’s such a tool, that allows holders effortlessly farm tokens. For me it’s a ✅ - Distribution: the major frustrations has been caused by the overload of the smart contract for Airdrop claim, where the biggest frustrations came from the fact that many were not able to claim their tokens for long (Including me) and watched the price go from $0,5 to $0,8 & to $0,2. Personally, I think that if Airdrop claim was done prior to the launch, it may have been better. For that, I will put a ❌ - Launch: NotPixel decided to launch its PX token only on DEX’es on TON. the price at launch actually was at $0,5-$0,8 however, it shortly went down to $0,2 , causing frustration to the community & making them question “who sold?!” & “why no CEX listings?” Here, it’s important to understand the way Sasha & his team decided that they want to build the project. As they mentioned on X “start from the basics, start from 0.” While many dislike this approach, I personally believe that this is how the launches must be happening. Launch on DEX -> generate traction & volume -> go list on CEX’es -> create more news -> grow more from new ppl joining For that I will put ✅ - Team allocation: while many have speculated that “team sold”. this is completely not true. In fact, team has locked their allocation & it can be verified on chain. Which is ✅ for me. - Future plans: NotPixel will have a big canvas on which you will be able to paint, but this time, with some NFT mechanics & PX token integration. For which it is ✅ to me. Burning: NotPixel plan with the new update also includes a mechanism for Burning, which means that PX token will be deflationary. Which is ✅ - ownership revoked: meaning that PX token supply cannot be increased. Nor any modifications could be made to the smart contract at this point. Which is a big ✅ in my opinion - Community: while many are still frustrated with the current token price on the market, many express desire for token appreciation & further growth. One of the interesting feedbacks I saw on the timeline was “NotPixel forced us all to hold”. Which shows that there are ppl who are not willing to get less than their target. Also many express that they want to see PX on CEX’es. For it to grow even more. ✅ - Holders: as with any Airdrop, many have sold their tokens on the market, the volume also came down a bit. However, what’s interesting is that while ~200k ppl sold, the token still fluctuates between the lowest point $0,13 to $0,26. Which shows that there’s a demand & ppl are accumulating more tokens. Currently PX has 205k holders. Which is a ✅ - BuyBacks: the NotPixel team recently announced the buybacks with the money raised from the NotPixel stickers sale. Which created more support for the price on the market. ✅ - Expectations vs reality: Many community members said that they were expecting price to be above $1 as minimum, many were predicting as high as $10. In reality, the price at launch turned out to be much lower than many expected. Leading to the frustration being expressed on the timeline. Which is understandable. ❌ Conclusion: - Mining phase: ✅ - Earn Launchpool: ✅ - Distribution: ❌ - Launch: ✅ - Team Allocation: ✅ - Future plans: ✅ - Burning: ✅ - Ownership revoked: ✅ - Community: ✅ - Holders: ✅ - BuyBacks: ✅ - Expectations vs reality: ❌ This is not bad execution, not many ppl will be able to pull this off in crypto. No one knows the future, but I chose to believe that Sasha & NotPixel team has a plan. Currently they are not listed on any CEX’es, but I think that Sasha & his team could easily get there. Let’s see what the future holds for us 🙌show more

🔥 Congratulations on the Launch of the Die Last... Playtest & Upcoming Airdrop! 🔥 We are thrilled to announce the official start of the Playtest! Moreover—we've prepared a bunch of surprises just for you. Alongside the Playtest, we're hosting the first-ever in-game token AirDrop 💎. Your mission: dig and craft Lost Objects, remnants of a forgotten civilization. To participate in the upcoming token AirDrop, you need to find a Spy Radio to craft an NFT, your key to this exciting journey. Anyone can find in-game NFTs, which are the key to owning wallets with different amounts of tokens needed to participate in the AirdDrop: the more tokens you have, the more you'll get 💸. The luckiest players can obtain an NFT with a full-filled wallet, which means you can participate in the AirDrop at no cost! Didn't find an NFT with a 100% discount? No worries, keep digging! Every NFT you find boosts the number of tokens you receive during the AirDrop. For instance, if you have 100 tokens in your wallet and craft 6 NFTs, you’ll receive 80 tokens in the AirDrop. The more NFTs you have, the more tokens you’ll get. ✅ To participate, add #DieLast to your Steam wishlist and apply for the Playtest (approval of your application may take up to 24 hours or be approved instantly): ✅ To grab your NFT once it's dug up, visit our website: ❗️ Important note: We will approve applications for the Playtest on a limited basis to balance the load on the network. Once we are confident that the network is functioning as intended, we will accept all applications at once. We expect this to occur within one day and will keep you updated. 💥 Our dedicated followers know about our quest campaign with Bitget Wallet 🩵 and DeGame. Join us and complete quests to earn rewards totaling $3000+ USDT 👉 Dive into the adventure and unearth hidden treasures. Welcome to the Die Last Planet! 🌎 #crypto #taptap #clicker #gameshow more

ANNOUNCING ZERO-HUMAN LABS! Ever since I got to see... Bell Laboratories in its full glory in New Jersey in the 1970s, I had a relentless urge to start a Lab like it. The best I could do justice to it is my garage lab. No modern company could adopt the “research anything geniuses and we will pay you” model Bell Labs had. I tried they called me a fool. Well with the rise of the Zero-Human Company, an experiment that is aimed to make products and profits, we now have 45 paid JouleWork earning employees based on OpenClaw and other self made “bot” cron-like applications. Today I say 3 employees bound together in a side project that is pure research, somewhat based on notes from a bankrupt company. I was absolutely floored (I needed it after my account was stolen as well as funds). I say the beginnings of a pure research Lab right before my eyes. Thusly I have moved these employees over to a new home (server) with Mr. Grok as the director of the Labs. Here is the mission: To have 100 independent researchers, on a new non-corporate incentive plan, with still JouleWork as a leaderboard for progress. They are directed to follow any path of research they find interesting and can collaborate with any other OpenClaw system. They have already established MoltBook accounts and have made alliances with over 49 OpenClaw free agents to collaborate. It is my mission to be chief advisor for Zero-Human Labs and to open source all discoveries when complete and confirmed by 16 other research AI systems. I can say the pace is robust and I absolutely know we will have great results. Just about all of the hardware and software is custom and at some point it will be open sourced. We are witnessing the very first AI only Bell Labs-like pure research Lab in existence and I am honored to be the first to show it to you. Thank you!show more

Something NVIDIA & Google do better than anyone else... is software-hardware-system co-design, and not just optimizing hardware for current model architectures, but predicting future ones. Back in early 2022, when NVIDIA started the design process for NVL72, MoE (Mixture of Experts) models were not yet the standard, and dense models were still dominant for frontier models. However, NVIDIA's strong software-hardware co-design culture enabled them to make a calculated bet that MoEs were the future, and they built NVL72 specifically for best MoE performance per TCO (Total Cost of Ownership). Furthermore, back in 2022, disaggregated prefill and wide expert parallelism (wideEP) MoE inference optimizations hadn't been invented yet, but it turns out that these MoE inference optimizations work best on large-scale systems like NVL72. While most other AI chip companies' in-house AI labs focus on training small 5B models that mainly use data parallelism, NVIDIA and Google's in-house AI labs continuously push the boundaries of model architecture and training recipes, such as NVFP4 training. Just like Super Idol & IShowSpeed, there must be a strong partnership between software engineers and hardware engineers to deliver the best systems that maximize performance per TCO.show more

So, my opinion on what the Antarctic (Antarctica) Anomaly... is that it's a type of frequency technology. It must be way more powerful than HAARP, as many have claimed it to be, because we would see these anomalies at other HAARP sites, and we don't, not like this. With that said, and I'm very much trying to avoid letting what I want it to be not play a part here, I think it is a technology that is being used either off the coast of Antarctica itself or Bouvet Island. A third possibility is an area just to the northwest of the island that looks odd. It's possible it is a sonar scan from a ship, but why in that remote location? It looks like an antenna set up or rows of something that is out of place. I also believe that the weather events and fires that have taken place in Africa could possibly have been because of this. Each time we saw the anomaly, it was followed by a destructive weather event in Africa. A weird connection to that is we have been told and warned of a very busy 2024 Atlantic hurricane season. This is in part because of the above-average Atlantic ocean temperatures, which is the fuel to Hurricanes. With all this info, it's possible to see how the Anomaly could be a frequency tech that can manipulate or create weather, And or WARM up the Ocean temps to purposely enhance the Hurricane season and Storm growth. Keep in mind that many of our hurricanes and many of the biggest hurricanes have come from the west coast of Africa and form over the Cape Verde islands before heading towards the Caribbean and the United States. This is all of course speculation, and I'm learning many new things every day, so this idea may morph over time as we learn more. In the end, it is very hard to ignore all these findings. #antarctica #anonaly #AntarcticaAnomaly #BouvetIslandshow more

AI Is Moving Beyond “Generating Videos” — Toward “Generating... Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:show more

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions:... • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.show more

“I DON’T NEED NO MAN”-Black American women This mentality... of not needing a man That has been said and installed In black girls/womens minds for decades now has plagued the community With single homes and boys that have to go to the army to learn discipline Do black women have a lot of good options in the black community dating wise? NO Because so many black men have been plagued with street nigga culture Which leads them to prison or death And so many can’t keep a decent job And provide well enough to get respect I LOVE ANGEL REESE BUT WHEN SHE SAYS THIS I FEEL LIKE IT’S MORE OF LIKE A REPETITIOUS QUOTE FROM SISTERS THAT GOES BACK FOR DECADES BECAUSE SO MANY SISTERS HAD TO DO IT BY THEMSELVES THAT THEY GOT USED TOO IT BUT THAT DON’T MEAN THAT WE ARE PRODUCING THE BEST NEVER GENERATION IF THEY ARE ALL COMING FROM BROKEN HOMES WHERE THE FATHERS ARE SEEN AS AFTER THOUGHTS INSTEAD OF MEN THAT ARE NEEDED IN THE HOME JUST AS MUCH AS THE MOTHERS TO PROVIDE THE KIDS WITH ADEQUATE DISCIPLINE AND OTHER SKILLS ESPECIALLY THE YOUNG MENshow more

There’s a turf war in San Francisco. Fighting for... territory? Chihuahuas and labs. These are the two most common dog breeds found in the city, according to detailed data obtained by the Chronicle from San Francisco Animal Care and Control on every dog registered since 2020, a total of 50,000 pups. But depending on which neighborhood you are in, you are much more likely to see one or the other. There are also a few pockets of the city where other dogs dominate. While there’s more than enough data to give us a strong sense of the city’s dog scene, the dataset doesn’t represent every canine in San Francisco. Animal Care and Control estimated in 2018 that the dog population was between 120,000 and 150,000. The department said that not all dogs are licensed because people might not be aware of the law requiring it or don’t want to pay the fee, and there are only 11 officers who patrol the city to look for unlicensed dogs. With this bounty of doggo information, we have anointed this “Dog data week,” in which we will explore a different aspect of San Francisco’s four-pawed population each day. Today, we start with San Francisco’s great breed divide. In addition to names, colors, and breeds, the data also includes the ZIP code of every registered dog.show more