#LLM #MLLM #WorldModel Working at @Kling_ai
Beijing, China
Joined June 2020
- Tweets855
- Following932
- Followers4.6K
- Likes1.3K
Zekun Wang (ZenMoore) 🔥 retweeted
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
Zekun Wang (ZenMoore) 🔥 retweeted
0/n
# Toward Human-Like RSI
Blog / project: self-developing-agents.githu…
Recursive self-improvement (RSI) is often pictured as a model repeatedly rewriting its own weights against a fixed objective. Humans improve differently: we decide what “better” means when the goal is vague, test ourselves, judge what happened, and change both what we know and the tools we work with.
This three-paper series turns those parts of improvement into controlled, auditable research questions:
ASPIRE studies how agents decide *what* to learn from a vague goal;
S³Gym studies how they test, judge, and learn from noisy self-generated experience;
HarnessDev studies how they build and evolve the external systems that shape their behavior.
These benchmarks use hidden evaluation as a proxy for whether a change transfers beyond the agent's own local signals - they do not claim to demonstrate open-ended RSI.
Zekun Wang (ZenMoore) 🔥 retweeted
Introducing 3AGameFactory: github.com/OpenDCAI/GameFact… — a skill and reference code framework designed for 3A game development. It covers image, 3D asset, motion, audio, and CG generation tools, along with reference code for UE5, Blender, Unity3D, and three.js. We welcome your stars!
Kudos to Yuran!
The proposed method dynamically updates the teacher’s guidance context according to the student’s evolving training state and employs a specialized mathematical formulation to improve the stability and effectiveness of OPD.
🚀 Introducing Flux-OPD, an OPD paradigm that uses evolving contexts as in-training supervision to capture task preferences in open-ended domains.
🧩 It improves video prompt optimization and medical question answering.
📄 arxiv.org/abs/2607.28022
🤗 huggingface.co/papers/2607.2…
Zekun Wang (ZenMoore) 🔥 retweeted
Huge congratulations to PKU alumni Wang Hong and Deng Yu, recipients of the 2026 Fields Medal — mathematics’ highest honor! 🧮
Announced at the 2026 International Congress of Mathematicians (ICM) in Philadelphia, the pair are among four mathematicians worldwide to claim this prestigious prize, awarded every four years to outstanding scholars under 40.
The awards are historic on several levels.
—First time two mathematicians who completed undergraduate studies in mainland China win the Fields Medal in the same year.
—Both joined Peking University as undergraduates in 2007.
—Wang Hong becomes only the third female Fields Medalist ever, the first Chinese woman, and the first recipient with a bachelor’s degree from a mainland Chinese university.
We are immensely proud of their extraordinary breakthroughs and lasting contributions to global mathematics.
Zekun Wang (ZenMoore) 🔥 retweeted
As long-horizon software engineering tasks grow in complexity, a single agent can no longer finish the tasks alone — effective multi-agent collaboration becomes necessary.
This leads to a natural question: how can multiple agents be coordinated to asynchronously collaborate over a shared artifact in an effective way?
We answer this question in our new preprint: Effective Strategies for Asynchronous Software Engineering Agents!
We suggest that to coordinate multiple software engineering agents, branch-and-merge is the key coordination mechanism, and that human SWE primitives like git worktree, git commit, and git merge are all you need to support it.
(1/n)
Zekun Wang (ZenMoore) 🔥 retweeted
Our new work, OpenWorldLib, is a unified inference codebase for advanced world models. It aims to provide a clearer definition of world models and, within a unified framework, evaluate the upper bounds of existing world model-related methods.
Code link: github.com/OpenDCAI/OpenWorl…
Zekun Wang (ZenMoore) 🔥 retweeted
It’s extremely good that Anthropic has not backed down, and it’s siginficant that OpenAI has taken a similar stance.
In the future, there will be much more challenging situations of this nature, and it will be critical for the relevant leaders to rise up to the occasion, for fierce competitors to put their differences aside. Good to see that happen today.
Zekun Wang (ZenMoore) 🔥 retweeted
For decades, we’ve trained AI to chase rewards. But humans don’t just optimize outcomes. We experience, reflect, then learn.
Can AI do the same?
Introducing 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐭𝐢𝐚𝐥 𝐑𝐞𝐢𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠, a step toward AI that truly learn from experience.
Zekun Wang (ZenMoore) 🔥 retweeted
🚀 Introducing the Kling 3.0 Model: Everyone a Director. It’s Time.
An all-in-one creative engine that enables truly native multimodal creation.
- Superb Consistency: Your characters and elements, always locked in.
- Flexible Video Production: Create 15s clips with precise control, excellent video realism and customizable multi-shots.
- Upgraded Native Audio: Now supports multi-character reference, more languages and accents.
- Enhanced Image Generation: 4K Image output, new image series mode and more cinematic visuals.
Ultra subscribers get exclusive early access — now live on Web -> Kling AI.
Get ready to unlock your creative potential with our most advanced model yet.
[For the next 24 hours ONLY]
Follow, Comment & Retweet to win exclusive early access - we will select 10 winners in this post from the top ten 'Most liked replies'.
So which feature are you most excited about? Let us know in the comment!
We will contact you via your DM.
🔥Kling 3.0 is coming soon.
Zekun Wang (ZenMoore) 🔥 retweeted
Kling VIDEO 2.6 — See the Sound, Hear the Visual
"What is your most unforgettable moment from this year?"
For us, it's definitely this Omni Launch Week with O1 and 2.6 now available!
Share your most unforgettable moment using Kling 2.6, with natural voice, sound effects, and ambient sounds perfectly aligned with the visuals!
All visuals and audio in this video were generated with the Kling 2.6 model.