Vmax (@VmaxAI) - ملف تويتر | Zamantika Mersobahis Locabet

Vmax أُعيد تغريده

We are so excited to have @tensorfi joining @VmaxAI! Maxwill joins us from @Meta, where he was working RL and LLMs for recommendation. Previously, he has also worked @Tesla on the autopilot team and also in Quant finance at Kronos research. He also holds an MS in CS from Georgia Tech. Maxwill simultaneously understands pre-LLM RL fundamentals but also how to scale pipelines for RL training for modern recommendation systems. Maxwill is already levelling up our pipeline for automated environment design, pushing multiple PRs as soon as he joined. Really excited about the velocity of his contributions and excited to share more soon.

English

0

1

15

730

Vmax@VmaxAI·4 Mar

Welcome Geoffrey!

Augustine Mavor-Parker@MavorParker

So excited to welcome Geoffrey Bradway as Member of Technical Staff @VmaxAI. Geoffrey is a rare catch. He was an engineer at @GoogleDeepMind, Google for Youtube and also has experience in early stage companies, having been a previous @ycombinator founder and also VP of engineering at @numerai. Fitting the Vmax DNA, he has experience with RL before it was cool (doing RL all the way back in 2014). Outside of work, Geoffrey does some really cool art with robotic drawing machines. Cannot wait to share more about what he is cooking

English

0

1

8

633

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·26 Şub

PR review is one of the fast growing categories in AI for SWE, now you can benchmark agents on *real* PRs

Martian@withmartian

Introducing Code Review Bench v0: codereview.withmartian.com The first independent code review benchmark. 200,000+ PRs. Unbiased. Fully OSS. Updated daily. Tool performance highlights 🧵👇 Featuring: @augmentcode @baz_scm @claudeai @coderabbitai @cursor @GeminiApp @github @graphite @greptile @kilocode @OpenAIDevs @propelcode @QodoAI

English

0

1

7

903

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·19 Şub

So excited to have @lorenz_wlf join @VmaxAI as a research fellow this spring! At NeurIPS last year, we caught up with Lorenz, realised how aligned he is with our research vision and invited him to join us shortly after. Lorenz comes from the @FAICDT1 programme at UCL (where I did my PhD also) and is supervised by @mircomusolesi. Previously he worked on differential privacy and personalized recommender systems at Apple and did his undergrad in mathematics and statistics at Imperial College London. Lorenz’s research focuses on RL, RLHF and modular continually learning RL agents. He has contributed to papers in ICLR, TMLR and AI STATS. So excited for him to join us and accelerate our efforts on unsupervised environment design. You can read Lorenz's research in the replies. Much more to come.

English

3

24

1.8K

Vmax@VmaxAI·6 Şub

@yanjo115 👀

QME

0

2

153

John Y 🔸@yanjo115·6 Şub

New paper! We used Sparse Autoencoder (SAE) embeddings to understand how agent behavior actually changes during post training. We analyzed thousands of rollouts in a Diplomacy environment and uncovered generalized reward hacking, weird roleplay, and the root cause of an unsuccessful training run. All of which our LLM baseline couldn't find.

English

5

12

95

4.7K

Vmax أُعيد تغريده

South Park Commons@southpkcommons·5 Şub

22/ Reinforcement learning, but make it automated. @MavorParker & @matthewjsargent showed us how they’re generating long-horizon environments at @VmaxAI. vmax.ai

English

1

2

7

1.5K

Vmax@VmaxAI·3 Şub

@creus_roger @MavorParker 🫡💪

QME

0

2

49

Roger Creus Castanyer@creus_roger·3 Şub

Honored to join such a talented team! @MavorParker and Matthew are building something special at @VmaxAI 🚀 Thrilled to contribute to this vision and keep the momentum going!

Augustine Mavor-Parker@MavorParker

@VmaxAI is excited to have @creus_roger joining us as a research fellow! Roger is joining us from @Mila_Quebec where he works with @pcastr and @GlenBerseth. Roger Creus Castanyer is a brilliant RL researcher working on exploration, credit assignment, and skill discovery. He is also fresh off of a NeurIPS spotlight and a recently accepted paper to ICLR, you can find more of his research in the comments. Roger is significantly accelerating our research on automated environment design - looking forward to sharing what he is cooking!

English

1

17

1K

Vmax@VmaxAI·3 Şub

welcome Roger!

Augustine Mavor-Parker@MavorParker

@VmaxAI is excited to have @creus_roger joining us as a research fellow! Roger is joining us from @Mila_Quebec where he works with @pcastr and @GlenBerseth. Roger Creus Castanyer is a brilliant RL researcher working on exploration, credit assignment, and skill discovery. He is also fresh off of a NeurIPS spotlight and a recently accepted paper to ICLR, you can find more of his research in the comments. Roger is significantly accelerating our research on automated environment design - looking forward to sharing what he is cooking!

English

0

8

703

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·29 Oca

@VmaxAI As an initial step in this direction, we have built on top of methods like SWE-smith and BugPilot, adding to the list of repo profiles built by the swe-bench community

English

1

9

528

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·29 Oca

This is a preview of many more tasks to come for Ares!

Josh Greaves@joshgreaves_ml

ARES uses the Harbor task format ( @alexgshaw ). It comes with SWE-Bench Verified, TerminalBench2, SWESmith, and everything else in the Harbor ecosystem. We're also releasing 1k new JavaScript tasks with @VmaxAI ( @MavorParker @matthewjsargent ) to help the ecosystem grow.

English

1

5

19

1.7K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·29 Oca

RL progress is bottlenecked by infra for training and evaluation. @VmaxAI is excited to be partnering @withmartian, generating environments for the Agentic Research and Evaluation (ARES) framework

English

7

30

75

8.4K

Vmax أُعيد تغريده

Josh Greaves@joshgreaves_ml·29 Oca

ARES uses the Harbor task format ( @alexgshaw ). It comes with SWE-Bench Verified, TerminalBench2, SWESmith, and everything else in the Harbor ecosystem. We're also releasing 1k new JavaScript tasks with @VmaxAI ( @MavorParker @matthewjsargent ) to help the ecosystem grow.

English

1

3

15

5K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·13 Oca

Really excited for this 👀 reach out to josh!

Josh Greaves@joshgreaves_ml

I’m building a new RL tool for code agents. If you work in RL and want an early preview, DM me.

English

1

7

1.2K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·23 Ara

Which pre-LLM methods matter most in the LLM era? We hosted an off the record event with @danijarh (world models for robotics), @ashvinair (RL @cursor_ai) and @nikishin_evg (reasoning @OpenAI) to share their takes @southpkcommons.

San Francisco, CA 🇺🇸 English

4

12

37

7.7K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·10 Ara

The RL event @VmaxAI and @southpkcommons are organizing has a stacked panel of amazing researchers, whose work I have admired since my PhD, when RL was not as much of a hot topic as it is today. Here's a thread on our panelists 👇

English

1

8

34

4.6K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·7 Ara

At @VmaxAI, we take the bitter lesson seriously. Come get your Vmax chocolate at the scaling environments workshop @SEAWorkshop

English

4

7

38

1.9K

Vmax@VmaxAI·7 Ara

Very excited to sponsor the scaling environments workshop

SEA Workshop@SEAWorkshop

🚀 SEA Workshop is going LIVE TOMORROW! Join us at NeurIPS 2025 for a full day diving into the Scaling Environments for Agents featuring an incredible lineup of speakers and panelists： @egrefen @Mike_A_Merrill @mialon_gregoire @deepaknathani11 @jl_marino @syz0x1 @qhwang3 Anthony G. Cohn, Eric Sommerlade, @fredsala 📍 Upper Level Room 23ABC 🕘 08:00–17:00 Huge thanks to our sponsors: @TheInclusionAI (@AntLingAGI) @SnorkelAI @SonicjobsApp and @VmaxAI 🙌 🔥 Get ready for a day of insights and inspiring conversations!

English

0

4

9

1.1K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·6 Kas

At Vmax, we are automating the construction of RL environments and the post-training of agents. We are hiring members of technical staff and research fellows. Come join us in SF! (link to apply in comments).

English

5

32

78

18.4K

Vmax أُعيد تغريده

Augustine Mavor-Parker@MavorParker·11 Haz

RL is the agent-environment loop and we currently do not have enough environments! At @VmaxAI we're building a platform for environment creation.

South Park Commons@southpkcommons

5/ Vmax A lack of simulation environments is bottlenecking superintelligent agents. @matthewjsargent & @mavorparker gave us a peek at Vmax’s platform—where they’re building new environments for reinforcement learning.

English

11