📢📢📢Introducing xGen-MM-Vid (BLIP-3-Video)! This highly efficient multimodal language model... is laser-focused on video understanding. Compared to other models, xGen-MM-Vid represents a video with a fraction of the visual tokens (e.g., 32 vs. 4608 tokens). Paper: Website: Researcher’s 🧵:👇show more

📢Introducing Generated Reality📢 A world model for XR that... turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4show more

📢📢📢 Check out XCube, a generative model for very-high... resolution 3D shapes and scenes! Project Page: Project Video: Props to Xuanchi Ren for leading this project!!!! [1/N]show more

📢📢📢 Tell me how Tinubu and Wike will manage... to sleep well tonight after watching this video. A New Nigeria is POssible ✌️show more

Apparently SeeDance 2 is down for the time being... on BytePlus but here's a young wizard with his dragon companion. It's a very cool video model. This video cost $0.72 USD to generate which seems reasonable. (300,000 tokens for a 15 secs at $0.0024 USD per 1000 tokens.)show more

With today’s 25 mm of rain, #Bengaluru has received... a total of 270 mm this May — putting the city on track to potentially record its highest May rainfall ever. #BengaluruRains #BengaluruTraffic Video - Khajashow more

VID SOLD! Stretched 14 mm septum extreme play video... 🔥 Check it out! #MVSales @manyvidsshow more

We took a 30B model and split it in... two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.show more

📢 New Listing Alert! 🐱 $HAPPY lands on Uphold... in 2 Days. The internet’s favorite “Happy Happy Happy” cat is coming to the #blockchain! With a fair launch and 3.33B tokens in circulation, this #Solana-based #memecoin is 100% community driven. 👇 Check our blog to learn more.show more

NVIDIA just released a very impressive text-to-video paper. Video... Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:show more

How Moving Atoms accurately converts Lidar/Slam scans into full... 3d building Info Models. 1. Capture: the raw laser scan (here, 54M points) is reconstructed into a dense, photoreal Gaussian splat. 2. Model: every pipe, fitting, valve and steel member is built as a native BIM element. 3. Heatmap: every scan point is checked against the model, and gaps and misfits are flagged automatically. 4. Measure: cross-sections are fitted to the real points, e.g. a Ø170 mm header at a 3.7 mm median error. 5. Rebuild: the model is refitted and exported as native Revit families and IFC. Scan is returned within 48 hours. The final model sits within 2.1 mm median of the scan. Send us a scan and see what comes back.show more

Today at #GoogleIO we've announced: 🤖 Project Astra: our... vision for AI assistants 🎨 Imagen 3 & Veo: our new image and video gen models ♊ Gemini 1.5 Flash: a light-weight multimodal model with long context & 1.5 Pro with 2M tokens... "Tuesday" as we call it Google DeepMindshow more

Melody: "This is the funnest shit ever"📢📢📢📢📢📢📢📢#BB28 #BBBitez

📢||◤3 Days◢|| Until the #Squadra Half-Year Anniversary! The #GekishinSquadra... Half-Year Anniversary is on 3/18 (PT)!🎉 We've released a countdown video!🎦 #DragonBallshow more

MiniMax-H3 open source: a general-purpose multimodal generative model that... unified understanding of multimodalof text, images, video, and audio, and is capable of generating audio and video with native stereo sound, supporting up to 15 seconds at 2K resolution.show more

China is literally on 🔥 Baidu from China has... launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.show more

BREAKING: Grok set a new record on OpenRouter this... year with over 16 trillion tokens of usage. 16,060,000,000,000 tokens. That is about 64% more usage than the next closest model.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