Wei Jiang retweeted
And now the demo is online as well. If you've seen all the cool visuals that Jeongi created, you can now try them yourself with your own images. Fun fact: it takes longer to render things than to solve things with Solv3R.
We just released Solv3R on 🤗 HuggingFace Space!
🔗 huggingface.co/spaces/jgkwak…
Try our interactive demo with your own images and see how Solv3R reconstructs your scene in 3D! 🚀
Wei Jiang retweeted
4K image generation in 10 seconds! ⚡
Meet MiniMax H3-Image.
16 million pixel resolution. Stunning realism. Precise prompt following & editing. Up to 16 reference images. All in 10 seconds.
And it's open-weight. 🚀
Available now via our API, MiniMax Code, and Hailuo AI — with 50% off 16MP+ generations during launch week!
Can't wait to see what you create. 🔥
Hugging Face: huggingface.co/MiniMaxAI/Min…
API: platform.minimax.io/docs/gui…
MiniMax Code: code.minimax.io/about
Wei Jiang retweeted
Code and weights are now available here: github.com/ubc-vision/solv3r
📢📢📢 Introducing 𝐒𝐨𝐥𝐯𝟑𝐑
Can geometric foundation models move beyond fixed-set prediction and keep solving like classical SfM?
We turn a looped Transformer into a reusable 𝐥𝐞𝐚𝐫𝐧𝐞𝐝 𝐠𝐞𝐨𝐦𝐞𝐭𝐫𝐢𝐜 𝐬𝐨𝐥𝐯𝐞𝐫
🌐 Project: ubc-vision.github.io/solv3r
🧵👇
Today we are releasing JST-2, the world's first full-stack physics-native world foundation model.
Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D.
Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.
Wei Jiang retweeted
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
Wei Jiang retweeted
Schnaus et al., "Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data"
Linked-in structures learned from different modalities on different datasets seem to share a lot of the geometry. And alignment between them can give some coarse translation.
DINOv2 has never seen a caption, and Qwen3 has never seen an image. We still aligned their embedding spaces without a single image-caption pair.
It even works when the images and the captions come from different datasets.
Project page: dominik-schnaus.github.io/un…
⬇️
Wei Jiang retweeted
Over the weekend, I created this. A quick open-source dictation tool that can also compose and edit based on screen content, your contacts, calendar, notes, reminders, or even Spotlight search. You can easily connect to your own backend, or mine, with ZDR.
In response to the ZCode product security issues reported by the community, we have completed the necessary remediation and sincerely apologize to all our users.
We have open-sourced ZCode at github.com/zai-org/ZCode, placing the code under community scrutiny and making ZCode more open and transparent.
We sincerely thank the community developers who previously identified issues in ZCode. Going forward, we will establish an ongoing product security vulnerability reporting and response process. We welcome developers to continue reviewing ZCode and reporting potential issues, and we will provide rewards based on the severity of the issues reported.
With respect to the code data referenced by the community, we confirm that no such data is retained and that it has never been used for model training.
Following the remediation, we invited the China Academy of Information and Communications Technology (CAICT) and NSFOCUS to conduct security assessments. The results are as follows:
Through its technical assessment, CAICT confirmed that the zcode-prod Alibaba Cloud OSS bucket is in a zero-data state. Security remediation has been completed in the ZCode v3.14.0 client. The Repo Wiki feature has been removed, and the workflow for generating and uploading local repository snapshots has been disabled.
NSFOCUS confirmed that all data objects in the zcode-prod Alibaba Cloud OSS bucket, as well as the bucket itself, have been deleted. Remediation has been completed in the ZCode v3.14.0 client. The Repo Wiki entry point and the associated generation workflow have been removed, and no functional path capable of triggering the generation of local repository snapshots or transmitting local files externally was identified.
Once again, we sincerely apologize and welcome continued scrutiny from the community. The full security assessment report will be released soon.















