←
Zichen Liu604 posts
Zichen Liu avatar

Zichen Liu

@zzlccc

Gemini RL @GoogleDeepMind

◷ Joined October 2021▧ 84 Photos and videos
Jensen Huang avatar
⟳ Zichen Liu retweeted
Jensen Huang@JensenHuang·Jul 24

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by every country. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. The world needs both frontier closed models and frontier open models. images.nvidia.com/pdf/Open-W…

Post attachmentPost attachmentPost attachment
Yi Tay avatar
⟳ Zichen Liu retweeted
Yi Tay@YiTayML·Nov 12

Hydrogen!

Meet Gemini 4 Hydrogen: built for rapid coding, multimodal synthesis, and everyday workflows. It finishes tasks 2.5x faster than 3.8 Flash and surpasses Argon on the @ArtificialAnlys Intelligence Index.

Post attachment
Zichen Liu avatar
Zichen Liu@zzlccc·Oct 28

Nothing is more exciting than the progress of the last 2 weeks, from Argon to Carbon. What a time to be working on Gemini!

I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model. Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching. We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards. As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!

Post attachment
Yi Tay avatar
⟳ Zichen Liu retweeted
Yi Tay@YiTayML·Oct 28

Gemini 4 Carbon is the best frontier model right now! 😎 Sota on AA index and a bunch of other stuff! 😎 Exciting times!

I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model. Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching. We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards. As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!

Post attachment
Zichen Liu avatar
Zichen Liu@zzlccc·Oct 1

It’s an awesome co-worker, and hope you enjoy Argon as much as we do!

Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.

Post attachment
Yi Tay avatar
⟳ Zichen Liu retweeted
Yi Tay@YiTayML·Sep 30

Gemini 4 is here! 🚀 And it outperforms astra/fable on many things 😇🤓

Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.

Post attachment
Zichen Liu avatar
Zichen Liu@zzlccc·Sep 21

Maybe self centering is a way to optimise my life trajectory, in Chinese it’s 知行合一

Tianyu Pang avatar
⟳ Zichen Liu retweeted
Tianyu Pang@TianyuPang1·Aug 20

HyCreator: an agent harness for long video generation 🚀 End2end Auto Mode ⏲️ Generate 10-minute scale films with zero human intervention 👨‍🦰 Switch to real-time interactive editing whenever you want Apply for early access: hycreator.tencent.com/

4:01
Zhi Zheng avatar
⟳ Zichen Liu retweeted
Zhi Zheng@zhengzhi20·Aug 19

🚀 Will Agentic ESOpt Be the Future of Long-Horizon Agentic Fine-Tuning? Excited to share our new work on Arxiv. Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Memory Requirements As LLM agents become longer-horizon and more branching, conventional Agentic RL faces three growing bottlenecks: high training/memory cost and increasingly challenging long-horizon credit assignment. Our Agentic ESOpt approaches agent fine-tuning from the parameter space instead, targeting three advantages: ⚡ Model Scalability — only minimal inference-level GPU memory requirement 🔧 Flexibility — prompt/skill–parameter co-evolution ⏳ Long-Horizon Scalability — trajectory-level parameter attribution without horizon-wise decomposition There are impressive empirical results, and we believe ES may be a better-matched parameter fine-tuning paradigm as agents become larger and longer-horizon. 📄 Paper: arxiv.org/abs/2608.17310 🌐 Project: zz1358m.github.io/Project-Ag… 💻 GitHub: github.com/zz1358m/Agentic-E… 🤗 Models & Checkpoints: huggingface.co/collections/z… Code, training logs, and checkpoints have been fully open-sourced. Main takeaways ↓

Post attachment
Bo Liu (Benjamin Liu) avatar
⟳ Zichen Liu retweeted
Bo Liu (Benjamin Liu)@Benjamin_eecs·Aug 20

Continuous self-improvement needs an ever-expanding supply of training environments (goals). SPADE: one model self-plays the Environment Designer and the Reasoning Agent, writing executable, agentic environments that get harder as it improves. Environment scaling on its own. ♠️

0:31
Simon Yu avatar
⟳ Zichen Liu retweeted
Simon Yu@simon_ycl·Aug 7

PI is cooking again, multi-agent RL support just landed in verifiers + prime-rl. Glad to see SPIRAL's Role-conditioned Advantage Estimation (RAE) featured and implemented for self-play!

Post attachment

Today, we’re extending our RL stack beyond individual agents to multi-agent systems. You can now express arbitrary agent interactions and train them. primeintellect.ai/blog/multi…

Zichen Liu avatar
Zichen Liu@zzlccc·Aug 6

Welcome submissions if you work on meta-agents!

🚀Call for Papers — @NeurIPSConf 2026 Workshop Workshop on Responsible Use of Meta-Agents 📅 December 11/12 · 📍 Sydney, Australia Join us to shape the future of Meta-Agents and Harness. Topics include but are not limited to: 1. Automated Design of Agent Harnesses 2. Optimization of Agentic Systems 3. Recursive Self-Improvement 4. Evaluation and Benchmarks for Meta-Agents 5. Misalignment and Safety for Meta-Agents 6. Governance & Human Oversight of Agents 🌟 Featuring an all-star speaker lineup: Graham Neubig @gneubig (CMU) Chelsea Finn @chelseabfinn (Stanford) Jenny Zhang @jennyzhangzt (Recursive) Robert Lange @RobertTLange (Sakana AI) Bo Li @uiuc_aisecure (UIUC) Hancheng Cao @CaoHancheng (Emory) Yuandong Tian @yuandongtian (Recursive) Chen Sun @ChenSun92 (Google DeepMind) Proudly sponsor by @metaai and @e2b Updates: Follow us here & spread the word! #NeurIPS2026 #MetaAgents #LLMs #Harness #RSI #SelfImprovement

Post attachment
Jeff Dean avatar
⟳ Zichen Liu retweeted
Jeff Dean@JeffDean·Aug 5

Announcing Discovery Loop! I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoLoopAI), a Public Benefit Corporation whose mission is to automate machine learning, science, and engineering to accelerate discoveries and progress. The four of us have worked together for 14 to 30 years, and have helped build some of the world’s most used products, infrastructure and AI models, and we’re excited to turn our attention to this ambitious endeavor. ♾ Learn more at: discoveryloop.com

Post attachmentPost attachment
yi avatar
⟳ Zichen Liu retweeted
yi@agihippo·Jul 10

Hello. If you're ultra exceptional ai researcher or engineer and want to work with me and my team in gdm sg Gemini team, please reach out.

Yi Tay avatar
⟳ Zichen Liu retweeted
Yi Tay@YiTayML·Jun 16

A few months ago, @qx_dong turned me from a pure IC into a manager. 🤗 Was a really fun experience so far watching people join one by one, building the team culture together and going up on the frontline. 🫠 Unprecedented moment in the history of Singapore to have so many talented researchers in one place. I'm glad to be building this legendary team. 🫡

Overdue update: I’ve joined @GoogleDeepMind as a research scientist to work on 💎Gemini post-training. Feeling incredibly fortunate to be cooking models with such a brilliant team, under the leadership of Yi Tay (@YiTayML) and Quoc Le (@quocleix). In the past a few month, we've found so much enjoyment in working with our own models and keeping pushing their boundaries. Ps, there's a special joy in creating recipes and internally naming them after our favorite drinks🧋 Looking forward to keep enjoying research, pushing the frontiers of Gemini and seeing the magic unfold on the path to AGI!

Post attachment