Ziniu Hu (@acbuller) / X

Ziniu Hu

171 posts

Ziniu Hu

@acbuller

Coding @AIatMeta TBD | Ex: @xAI @GoogleDeepMind @Caltech @UCLA

Los Angeles, CA

Joined June 2020

Pinned
Ziniu Hu
@acbuller
Jul 9
Been working on improving the real-world coding usefulness for muse spark 1.1 The model can autonomously solve many daily coding tasks, with much cheaper prices than competitors' models. Please try it on coding products and let us know if you have any feedback.
Alexandr Wang
@alexandr_wang
Jul 9
1/ muse spark 1.1 is an industry-competitive agentic and coding model. across many agentic evals it rivals gpt-5.5 and opus-4.8. available now through the new meta model api and in meta ai. 🧵
Ziniu Hu
@acbuller
Dec 14, 2024
Been training Grok-2 to improve its general instruction-following in past months. Excited to release it to everyone for free. Try our free API with $25 free credit as well!
SpaceXAI
@SpaceXAI
Dec 14, 2024
x.ai/blog/grok-1212
Ziniu Hu
@acbuller
Feb 18, 2025
做了一点微小的工作 No.1
Arena.ai
@arena
Feb 18, 2025
BREAKING: @xai early version of Grok-3 (codename "chocolate") is now #1 in Arena! 🏆 Grok-3 is: - First-ever model to break 1400 score! - #1 across all categories, a milestone that keeps getting harder to achieve Huge congratulations to @xai on this milestone! View thread 🧵
Ziniu Hu
@acbuller
Aug 28, 2025
Been training the Grok Code Fast 1 model with the incredible team. It's a blazing fast model 🚀 that can solve a broad range of real-world agentic coding tasks. Excited to share it with the world, hope it help with your work!
SpaceXAI
@SpaceXAI
Aug 28, 2025
Introducing Grok Code Fast 1, a speedy and economical reasoning model that excels at agentic coding. Now available for free on GitHub Copilot, Cursor, Cline, Kilo Code, Roo Code, opencode, and Windsurf. x.ai/news/grok-code…
Ziniu Hu
@acbuller
Jul 10, 2025
Grok 4 is living 🚀
Ziniu Hu
@acbuller
Feb 20, 2025
In past months I saw some posts saying Reasoning models cannot do agent tasks. Try Grok Deepsearch that combines the world of two for free 🚀
SpaceXAI
@SpaceXAI
Feb 20, 2025
This is it: The world’s smartest AI, Grok 3, now available for free (until our servers melt). Try Grok 3 now: x.com/i/grok X Premium+ and SuperGrok users will have increased access to Grok 3, in addition to early access to advanced features like Voice Mode
00:00
Ziniu Hu
@acbuller
Apr 18, 2025
Been working on Post-Training the grok3-mini reasoning models, combining Reasoning and Function-Calling capabilities for building your agents. Don't forget our 150$ free credits to get started with these models: docs.x.ai/docs/data-shar…
SpaceXAI
@SpaceXAI
Apr 18, 2025
Meet the Grok 3 family, now on our API! Grok 3 Mini outperforms reasoning models at 5x lower cost, redefining cost-efficient intelligence. Grok 3, the world's strongest non-reasoning model, excels in tasks that need real world knowledge like law, finance, and healthcare.
Ziniu Hu
@acbuller
Aug 27, 2024
Thrilled to receive the KDD Dissertation Award Runner-Up, for my PhD works on Neural-Symbolic Reasoning. Sincerely thanks to my PhD advisors @YizhouSun and @kaiwei_chang, my letter supporters @yisongyue and @JHamrick. Thanks to the award committee @kdd_news for such honor.
00:00
Ziniu Hu
@acbuller
Dec 12, 2023
Interested in LLM + Tool-Use, via Tree-Search? This afternoon in #NeurIPS2023, #215, I'll present "AVIS: Autonomous Visual Information Seeking with Large Language Model Agent" (blog.research.google/2023/08/autono…) Feel free to drop by and chat.
research.google
Autonomous visual information seeking with large language models
Posted by Ziniu Hu, Student Researcher, and Alireza Fathi, Research Scientist, Google Research, Perception Team There has been great progress towar...
Ziniu Hu
@acbuller
Aug 18, 2023
🤔 How to let Large Language Models (LLMs) agent utilize diverse tools via Tree Search 🔍? In AVIS, we enable LLM Agent to dynamically traverse a transition graph with self-critic (when one path is not informative, backtrack to previous state). This achieves SOTA VQA result.
Google AI
@GoogleAI
Aug 18, 2023
Today on the blog, read all about AVIS — Autonomous Visual Information Seeking with Large Language Models — a novel method that iteratively employs a planner and reasoner to achieve state-of-the-art results on visual information seeking tasks → goo.gle/3P2y2mY
Ziniu Hu
@acbuller
Oct 10, 2023
Can LLMs play a hidden-identity board game "Renaissance Avalon"? Check out: arxiv.org/abs/2310.05036 Code: github.com/jonathanmli/Av… In this work, we built a game engine AvalonBench, consisting of several fixed rule baselines. We found ChatGPT 3.5 still cannot beat simple rules.
Ziniu Hu
@acbuller
Jun 8, 2024
How to control LLM behavior with LLM-as-a-judge? Check our paper: "Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller" Website: llm-self-control.github.io Paper: arxiv.org/abs/2406.02721 Code: github.com/HenryCai11/LLM…
Ziniu Hu
@acbuller
Aug 14, 2024
🪫🚀 🔋
SpaceXAI
@SpaceXAI
Aug 14, 2024
x.ai/blog/grok-2
Ziniu Hu
@acbuller
Nov 25, 2022
Excited to receive the #SoCalNLP Best Paper Award for our paper "Empowering Language Models with Knowledge Graph Reasoning for Question Answering". The paper link is: arxiv.org/abs/2211.08380 Thanks to the organizers and all the great collaborators!
UCSB AI
@UCSB_AI
Nov 20, 2022
Replying to @UCSB_AI
Our @MegagonLabs Best Paper Award winner was "Empowering Language Models with Knowledge Graph Reasoning for Question Answering" by Ziniu Hu et al from UCLA! Paper link: arxiv.org/abs/2211.08380 Thank you to award sponsor @MegagonLabs for supporting our event! (4/4)