Siliang Zeng

Research | Ex Bytedance Seed. Working on Agents and LLM Post-training.

[Rasool Fakoor @rasoolfa]

Exciting time to be at Modal 🚀 i'm hiring interns & full-time researchers in RL, ML, and large models to join our **new** research team. apply on our website or reach out to me directly (contact info on my website)!

[Lena @lena_z01]

Introducing yes&, the social platform built for creation.

Creativity has never happened in isolation. A style. A pose. A sound. An outfit. We draw inspiration from the work we admire, then turn it into something new.

But inspiration and creation have always lived in separate places. We save Pinterest boards, bookmark TikToks, screenshot Instagram posts, and fill our camera rolls with ideas, yet rarely turn them into creations of our own.

AI changes that.

On @yesand_ai, anything that inspires you can become a starting point. Discover great work, explore the prompts, skills, and creative process behind it, then remix it into something that’s yours.

Every remix preserves the lineage of the idea and recognizes the creators who helped shape it.

When creating becomes as simple as taking a photo, creativity naturally becomes social. Ideas evolve through inspiration, remixing, and co-creation.

Today, @markusmak12 and I are excited to share that we’ve raised $3M in pre-seed funding, led by @Accel , with support from @parable_vc and an incredible group of partners, to build the infrastructure for collaborative creativity.

Come make your next remix: https://t.co/FxQlg2ZTCn

[Siliang Zeng @ZengSiliang]

@QuanquanGu All the best, Prof. Gu!

[Brendan Hogan @brendanh0gan]

introducing AlphaLab -an autonomous system that runs quantitative research end-to-end

give it a dataset + goal, it explores, reads papers, builds evals, and runs parallel experiments across a GPU cluster, learning&evolving from the results

all details, code, and paper below

[Prime Intellect @PrimeIntellect]

Prime Intellect Day

Saturday — March 14 (Pi Day)
4-11pm — The Melody of SF

Talks on frontier model training, agentic RL, computer use, coding agents, diffusion LLMs, automating AI & science, robotics — and why the singularity will not be singular.

[Siliang Zeng @ZengSiliang]

Amazing @PrimeIntellect Day in the Church!

[Alex Wa @_djdumpling]

new blog! What methodologies do labs use to train frontier models?

The blog distills 7 open-weight model reports from frontier labs, covering architecture, stability, optimizers, data curation, pre/mid/post-training + RL, and behaviors/safety

https://t.co/88heRH4TcO

[Zephyr @zephyr_z9]

Best model on multimodal tasks

[Quanquan Gu @QuanquanGu]

Seed 2.0 is finally out! 🔥

[Siliang Zeng @ZengSiliang]

@philipjohnball Congrats! 🚀

[Siliang Zeng @ZengSiliang]

@LiaoZeyi 🚀🚀🚀 can’t wait to talk with you!

[Siliang Zeng @ZengSiliang]

@Tianyi2020 Big congrats!

[Siliang Zeng @ZengSiliang]

@brendanh0gan Amazing! Congrats, Brendan!

[Siliang Zeng @ZengSiliang]

@rasoolfa 🚀🚀🚀

[Siliang Zeng @ZengSiliang]

@willcb Thanks!!

[Siliang Zeng @ZengSiliang]

Thrilled to share that I’ve recently joined @ByteDance_Seed as a research scientist! My goal is to continue the research on RL and scale it towards impactful applications, especially agentic RL!

Excited for the journey towards AGI 🚀

[Mingyi_Hong @MingyiHong01]

Our recent work on exploring how RL with turn-level credit assignment helps multi-turn tasks.

[Siliang Zeng @ZengSiliang]

@_AndrewZhao Renaissance of RL

[Siliang Zeng @ZengSiliang]

Interesting project with @willcb @quanwei0 @Mingyi552237 and other collaborators. We show that turn-level credit assignment indeed helps a lot for multi-turn tasks.

Multi-turn task is the setting where we may think bringing MDP and other classic RL thoughts back to the table.

[will brown @willcb]

new paper with @ZengSiliang and other collaborators about some of our multi-turn findings from the past couple months :)

lots of experiments about the pros and cons of structured rewards and credit assignment, particularly relevant when doing tool-use RL with 7B models