Introducing #Rodin Gen-2.5🚀
🔥World’s 1st 10 MILLION polygon #3D GenAI — down to skin microstructures.
1️⃣1M-poly in 4s
2️⃣Adaptive thinking effort - just like LLMs
3️⃣3D-native textures, no blind spot
4️⃣Batch up to 10 results
💥Manual BANG to Parts & more...
🚨$1 for first mo!
We’ve released the official Blender add-on for ZOZO’s Contact Solver, our open-source physics solver developed at ZOZO, Inc. Blender users, please take a look!
https://t.co/t2kmcaCP2i
Your GLB is probably way too heavy.
AI models, scans, exports, they often land at 5–60MB+ with millions of tris. Brutal for games, apps, and real-time 3D.
I built GLB Shrink to help the dev community fix this:
drop → preview before/after → download
Real test: 58 MB → 869 KB (−99%)
Draco + WebP. No Blender. No CLI.
Free & open source 🎮
https://t.co/fe3MqDbfNK
#gamedev #indiegame
Introducing CozyBlanket Pro
A next-generation mesh optimization and cleanup toolkit, built from the ground up with AI-assisted retopology, cutting-edge UV tools, and powerful tool system to transform complex geometry into clean, efficient, production-ready assets.
Introducing the newest Coral board, for efficient, on-device AI!
Check out the demos in the video:
- On-board speech translation
- Natural language controlling hardware
- Vision & sound generating music
Introducing #Rodin Gen-2.5🚀
🔥World’s 1st 10 MILLION polygon #3D GenAI — down to skin microstructures.
1️⃣1M-poly in 4s
2️⃣Adaptive thinking effort - just like LLMs
3️⃣3D-native textures, no blind spot
4️⃣Batch up to 10 results
💥Manual BANG to Parts & more...
🚨$1 for first mo!
new release for text-to-cad, an open source CAD harness and skills for codex / claude:
- mechanism validation (go from text prompt to functional mechanical design)
- parameters + animations for step files
- extended sdf, srdf, urdf support
3k stars, 10k downloads, we cooking
We are releasing Carbon: a crazy fast DNA model
Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days.
Here are the tricks we used:
When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens.
Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure.
The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size.
We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life.
https://t.co/OWEUoxAFjG
Microsoft has released a 4B parameter model that turns any image into a 3D asset in 3 seconds.
It uses a new geometry format called O-Voxel that converts to a textured mesh in under 100ms on CUDA.
Outputs GLB files with full PBR textures, ready for Blender, Unity, and Unreal.
100% Open Source.
An open-weight alternative to ElevenLabs!
Voxtral is a TTS model by Mistral with:
- just 4B params
- 70ms latency for voice agents
- voice cloning from 3s of audio
- 9 languages + cross-lingual transfer
- 68.4% win rate over ElevenLabs Flash v2.5
Open weights on Hugging Face.
Today we release Lighthouse Attention, a selection-based hierarchical attention for long-context pre-training that delivers a 1.4-1.7× wall-clock speedup at 98K context.
It runs the same forward+backward pass ~17× faster than standard attention at 512K context on a single B200, without a custom sparse attention kernel, a straight-through estimator, or an auxiliary loss.
During training, queries, keys, and values are pooled symmetrically into a multi-resolution pyramid. We then score every pyramid heads, and a top-k cascade selects a small hierarchical dense sub-sequence, and after a sorting pass that enforces causality, we use standard attention for token mixing. A brief full attention resume at the end converts the checkpoint back into a competent dense-attention model.
Validated this using 530M parameter Llama-3 models across 50B tokens, with up to 1M-token benchmarks across 32 B200s under context parallelism.
The work on Lighthouse Attention was led by @bloc97_, @SubhoGhosh02, and @theemozilla.