Zekun Wang (ZenMoore) 🔥

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)

Some politicians are destroying science. They are sinners against history.

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/OpenW…

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.

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.

🚀 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 truly "one giant leap for AI video generation"! Check out this amazing mockumentary from Kling AI Creative Partner Simon Meyer!

Kling 3.0 Model is coming! Now in exclusive early access. Stay tuned for what’s next. 🚀

🔥Kling 3.0 is coming soon.

可灵2.6可以生成群口中文说唱了，歌曲未使用其他任何音乐模型。 所以可灵AI这次2.6的音画同出是可以生成完整歌曲的，也具备生成复杂音乐作品的潜力，尤其中文的表现很好，大家可以听听看，具体方法后面讲一下。 1. 完整群口西游说唱

The perfect bread cat! 🍞

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.

introducing Kling O1. this new model let's you edit videos with prompts and images – like Nano Banana but for video. try it now!

Do we finally have Nano Banana for video? Kling dropped O1 this morning - a new multimodal generation and editing model. You can upload a video + reference image(s) and prompt to add, delete, or swap. I turned my cat into a chihuahua ✨

🎉 Introducing Kling-Omni! 🌍 Be the director of your world! 🎬 From any instruction (video, prompt, image, subject), create any video!

This week, starting from Dec 1, we're launching something new every day — Five days straight, exciting features await! Follow along to witness some game changers for AI-powered content creation! 🎥✨ Stay tuned and don't miss out! #KlingOmniLaunchWeek

Thrilled to hit the 1000-citation milestone! I'm attending #EMNLP2025 in person in #Suzhou. Let's connect 🤗. We can have a coffee chat and enjoy the city together.

Thrilled to release new paper: “Scaling Latent Reasoning via Looped Language Models.” TLDR: We scale up loop language models to 2.6 billion parameters, and pretrained on > 7 trillion tokens. The resulting model is on par with SOTA language models of 2 to 3x size.

To push self-driving into situations wilder than reality, we built a neural network world simulator that can create entirely synthetic worlds for the Tesla to drive in. Video below is fully generated & not a real video

@webagentlab Awesome work from @kugwzk1 (lol, not me @ZenMoore1 )

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos VIDEOAGENTTREK is a scalable pipeline that automatically extracts structured training data for computer-use agents from unlabeled screen-recorded tutorial videos, significantly improving task success rates and step accuracy without the need for manual annotation. Dunjie Lu @DunjieLu1219 , Yiheng Xu @yihengxu_ , Junli Wang @JunliWang2021 , Haoyuan Wu, Xinyuan Wang @xywang626 , Zekun Wang @ZenMoore1 , Junlin Yang @junlin45300 , Hongjin Su @hongjin_su , Jixuan Chen @chenjx210734 , Junda Chen, Yuchen Mao, Jingren Zhou, Junyang Lin @JustinLin610 , Binyuan Hui @huybery , Tao Yu @taoyds The University of Hong Kong; Qwen Team; Alibaba Group arxiv.org/pdf/2510.19488

🚨#GUIAgent Papers of the Week(10/18～10/24): ◾️GhostEI-Bench ◾️MixKV ◾️Surfer 2 ◾️WebGraphEval ◾️ColorAgent ◾️DaMo ◾️See, Think, Act ◾️VideoAgentTrek ◾️WebDevJudge ◾️UltraCUA ◾️Branch-and-Browse check it out 👉 webagentlab.notion.site/paper