Yang Xu

Undergrad @ZJU_China CS | @Minimax_AI Pretraining |Deconstruction via Construction

[RyanLee @RyanLeeMiniMax]

Hey everyone �� our high-performance MSA kernel library is now open-source. The M3 weights are expected to drop this Friday. Thanks for waiting!
Github: https://t.co/7hixC7FNg7
Paper：https://t.co/t1nHSJgGwB

[余温 @gkxspace]

你的 AI Agent 现在能搜推特了。

Grok CLI 终于把 Twitter 的搜索能力给内置了。

X 官方搜索 API 很贵，Grok 这次加了 4 个搜索工具：

1、x_keyword_search：最强的一个，完整支持所有高级搜索操作符，from:、since:、min_faves:、filter:images，Top/Latest 模式都有
2、x_semantic_search：语义搜索推文，支持日期范围和��关性过滤
3、x_user_search：搜用户
4、x_thread_fetch：抓完整推文线程，父帖加所有回复

关键是这东西在本地，你的 Agent 随时能调用，背后直接连着 Twitter 实时���息，价值巨大。

[Ming-Yu Liu @liu_mingyu]

Introducing NVIDIA Cosmos 3

We released NVIDIA Cosmos 3 last night.

And today, seeing it take the top spots across 8+ open model leaderboards feels surreal. We spent months working towards this moment.

Here’s the breakdown:

The Leaderboard Wins

World Reasoning
🏆 #1 open model on VANTAGE-Bench for vision AI
🏆 #1 overall on Traffic Anomaly Reasoning (TAR)

World Generation
🏆 #1 open model on Artificial Analysis Image-to-Video leaderboard
🏆 #1 open model on Artificial Analysis Text-to-Image leaderboard
🏆 #1 open model on PAI-Bench for physical AI synthetic data generation
🏆 #1 open model on Physics-IQ, which measures accuracy on physical laws
🏆 #1 open model on R-Bench for world generation quality

World Action
🏆 #1 on RoboArena for specialized policy
🏆 #1 on RoboLab for action generation

But the leaderboards are only part of the story. The real story is why we built Cosmos 3 in the first place.

The Problem

Training robots and autonomous systems in the real world is painfully hard.

Robots need to try the same thing numerous times before they succeed reliably. Self-driving cars need rare edge cases that may never happen naturally. Smart machines need to understand physics, motion, contact, failure, and surprise.

And real-world data is slow, expensive, and sometimes dangerous to collect. At some point, the answer cannot just be “collect more data.”

You can’t collect your way out of an infinite physical world. You have to generate it.

That… was the question behind Cosmos: Can one model understand the physical world deeply enough to reason about it, simulate it, and generate actions inside it?

What We Built

Cosmos 3 is the first omni-model for physical AI. It can understand and generate across: language · images · video · audio · action sequences

It is not just a VLM.

Not just a video generator.

Not just a robot policy model.

It is all of them, in one single model.

That matters because physical AI has been fragmented for a long time. Cosmos 3 is our attempt to collapse that fragmentation.

Depending on how you configure the inputs and outputs, the same model can act as a vision-language model, a video/world generator, a world simulator, or a world-action model.

No separate architecture required.

The Architecture

Under the hood, Cosmos 3 uses a dual-tower Mixture-of-Transformers architecture.

One tower is autoregressive for reasoning. It handles next-token prediction for language and discrete understanding.

The other tower is diffusion-based- for generation. It denoises images, video, audio, and action trajectories.
Two towers. Dual-stream joint attention. One shared world representation.

Each modality gets its own tools: visual encoders, video VAEs, audio VAEs, and action projectors that can map different embodiments into a unified action space.

Action is a first-class modality in Cosmos 3.

That’s what makes it more than a video model. It doesn’t just predict and generate what the world might look like. It can connect reasoning and world modeling to physically grounded action.

Why This Matters

One of the most interesting findings from the ablation work is that training action domains together creates positive transfer.

That means adding more embodiments does not just add more use cases. It can actually make the model better.

This is the heart of why omnimodal training matters.

A shared world representation is not just convenient. It can make each individual task stronger. That’s the part that feels like the beginning of something much bigger.

The part I’m most excited about is that Cosmos 3 is fully open.

Developers get the models, scripts, optimization, inference endpoints, post-training recipes, datasets, and benchmarks.

Everything is available under the Linux Foundation’s OpenMDW 1.1 License.

You can use Cosmos 3 out of the box. You can use the VLM, world model, or world-action pieces separately.

You can post-train it for your own domain, embodiment, or accuracy target.

That’s what makes this feel different.

Cosmos 3 is not just a model release. It is the foundation for building intelligence for autonomous machines.

For me, Cosmos 3 feels like a step toward a world where physical AI development becomes much more scalable and accessible - to a new age of developers and agents.

That’s what we built Cosmos 3 for. I cannot wait to see what you build with it.

Download Models on Hugging Face
https://t.co/LAZoVygeim

Customize Models on GitHub
https://t.co/ZVQBNdqXDD

Read the Tech Blog to Learn More
https://t.co/Hn6Op9YeG1

[Sam Altman @sama]

OpenAI Robotics is hiring, looking for exceptional full-stack hardware, ops, systems, and ML engineers to help us program and manufacture robots that are useful for society.

AI should be able to help people in the physical world. In the short term, we are focused on robots to support skilled workers to build our future infrastructure; in the long term, we imagine everyone having a personal robot doing anything they need.

Our world simulation research program, led by Aditya Ramesh (@model_mechanic), has evolved over the past year into OpenAI Robotics. Progress is rapid, and based on a foundation of co-design between robotics hardware and ML research.

If you love working hands-on across the robotics stack and want to build the future, please consider joining us. Send an email with your background and evidence of exceptional accomplishment to: [email protected]

[Elliot Arledge @elliotarledge]

They used KernelBench-Hard! My benchmark is getting normalized!

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[MikaStars★ @MikaStars39]

Key takeaway from the M3 blog: M3 independently reproduce an ICLR 2025 Outstanding Paper Award winner, "Learning Dynamics of LLM Finetuning."

M3 ran autonomously for nearly 12 hours, producing 18 commits and 23 experimental figures on its own, and got the core experiments working:
- it matched the predicted probability trends in the SFT stage
- clearly observed the squeezing effect central to the DPO experiments
- validated the Extend mitigation method proposed in the original paper.

[Benhao Huang @huskydogewoof]

Introducing 🔁 Awesome-Loop-Models: a curated repo for keeping up with loop models!

Whether you are just entering the field or have been exploring loop models for a while, this repo is built to serve as an actively updated map for mechanism analysis, architecture and algorithm design, applications, and related directions.

🧵 [1/n]

[Yang Xu @YangXu_09]

@chelseabfinn @Anikait_Singh_ Excellent benchmark! And GIANTS-4B's performance is quite surprising. Gonna try using it on my own.

[Yang Xu @YangXu_09]

@siliconmania 😂🤣

[Ge Zhang @GeZhang86038849]

We start the research project, called adaptive training compute allocation, in ByteDance Seed one and a half year ago, because we believe that it is natural.

It has been a long and fasnating way to introduce Ouro / DLCM / ConceptMoE. It is still a long way.

[Frank Wang 玉伯 @lifesinger]

很赞同。一个企业最重要的，依旧是人，是组织，是构建这个组织的创始人的底色��

微软的底色是缺少品位的商人，Meta 的底色是太聪明的商人。缺少品位和太聪明，长期来看，会急，会陷入困境。

OpenAI 的底色很复杂。

Google 和 Anthropic 的底色有点类似。出发点里都有技术驱动和不作恶。或许这类公司，长期，会更有方向。组织效率整体会更高。

期待更多创业公司的底色更好。让整个世界的底色，也会因此不一样。

[Wentao Guo @WentaoGuo7]

🚀SonicMoE🚀now runs at peak throughput on NVIDIA Blackwell GPUs 😃

54% & 35% higher fwd/bwd TFLOPS than the DeepGEMM baseline and 21% higher fwd TFLOPS than the triton official example. SonicMoE still maintains its minimum activation memory footprint: the same as a dense model with equal activated parameters and independent of expert granularity. We wrote a blogpost on how we leveraged Blackwell features and the software abstraction on QuACK:

Work with @MayankMish98, @XinleC295, @istoica05, @tri_dao

[Dmitry Krotov @DimaKrotov]

This past week several people asked me about how Loop Transformers are related to Energy Transformers.

Energy Transformers are:
���� looped transformers
👉 energy-based models (EBMs)
👉 Dense Associative Memories — generalized Hopfield nets with superior scaling laws for information storage

That combo is powerful:
👉 looping = iterative refinement = reasoning in the latent space (not in token space)
👉 energy-based = stability of token dynamics
👉 Associative Memory = strong retrieval capabilities

Put together: models that settle into good solutions, not just predict next tokens.

I’ve been especially excited about this class of models for a while. They feel like a promising direction for more stable, interpretable, and memory-rich AI systems.

This week at #ICLR2026 we are presenting NRGPT https://t.co/UkXt54Dzhj, which is a:
👉 a looped transformer
👉 a stable Dense Associative Memory
👉 works great on ListOps and real text

Original Energy Transformer paper: https://t.co/UOfrwZXtOf from NeurIPS 2023

[Rui-Jie Zhu @RidgerZhu]

https://t.co/YG9P8U965p

[Yang Xu @YangXu_09]

@huskydogewoof @ChrisHayduk @KyeGomezB Cool!! thankyou. and I can't wait for the official release!

[Yang Xu @YangXu_09]

Learning on the Looped Transformer Thread (1/N)

I've been following the recent wave of work on looped/recurrent-depth transformers. Here are some interesting resources I've come across.

[Yang Xu @YangXu_09]

Good point on taste and ambition!! But for most PhD students, GPU access, budgets, and data constraints still bite hard. Agents reduce friction in coding and writing, but they do not remove the need for compute, careful evaluation, or sustained experimentation. So yes, ambition matters. But resources still determine which ambitious ideas get a real chance.

[Peter Steinberger 🦞 @steipete]

Kudos to the folks from Tencent for working with us and providing evals to improve OpenClaw's harness performance!

We're also working with them to bring fixes/improvements back to the open source repo.

Great option for folks not comfortable with the terminal.

[Yang Xu @YangXu_09]

@0xTykoo 有意思啊，感觉可以整一个🤔

[Tykoo @0xTykoo]

我觉得应该办一个全世界最健康的黑客松比赛，谁都他妈不许熬夜，一天不许工作超过8小时，定时离开电脑，让你的agent自己跑一晚上任务跑满且不浪费也是种能力，

每天强迫健身一次，大家一起吃健康餐（有点形式主义了）然后全都带上whoop手环，每天都要记录分数，算入成绩里，

我总感觉黑客松摄影老师们非要找角度抓拍大家四仰八叉、疲惫不堪的样子，其实挺病态的。