Ilya Zisman

RL i guess | | PhDing

[Ilya Zisman @suessmannn]

@mmbronstein все мы приехали сюда исполнять хрустальную мечту Остапа :)

[Ilya Zisman @suessmannn]

@nathanrmonette @EugeneVinitsky @nyutandon @FLAIR_Ox man congrats! that's a super cool place to be with an incredible advisor!!

[Ilya Zisman @suessmannn]

i-see-brasil
https://t.co/gQXLV6ZzPT

[Ilya Zisman @suessmannn]

🔥 Zero-shot generalization is the dream: adapt instantly, no fine-tuning. It's why LLMs blew up—but it's not just a language modeling thing. It’s happening in RL too.

🚨 @maxsbob21's new paper dives deep into zero-shot RL under shifting dynamics—and why current methods break.

[Ilya Zisman @suessmannn]

@how_uhh , Dr. Nikulin

[Ilya Zisman @suessmannn]

@how_uhh some more if u wish

[Ilya Zisman @suessmannn]

My dearest friend Sasha @how_uhh, congrats on successfully defending your AI PhD! Everyone please address him as Dr. Nikulin in the comments from now onwards!
ps: who’d have thought during our freshman year as Sociology majors [pic taken ~10 yrs ago] that I'd posting this tweet?

[Nikita Kachaev @judokach]

👀 Action fine-tuning often blinds VLA models: they lose the visual–language (VL) priors that made them smart. We show how to keep those priors intact with a tiny alignment loss. 🤖

↓

[Denis Tarasov @ML_is_overhyped]

I’m asking for help. I was meant to start my PhD with @_rockt and @robertarail at UCL, but my UK background check was refused. My appeal seems unlikely to succeed, so I’m urgently searching for any PhD or research positions in academia or industry. Any help is appreciated.

[vik @vikhyatk]

@GFaang97609 no i never run ablations, because i believe god has a plan

[Ilya Zisman @suessmannn]

@LeRobotHF hey, cool stuff! I submitted a POC of phone teleop to the LeRobot hackathon, glad you found it inspiring!
https://t.co/so6xkadPkE

[Ilya Zisman @suessmannn]

Had a blast together with @how_uhh at @LeRobotHF hackathon this weekend. Built phone-based teleoperation for my SO-100 arm using pose estimation. Here’s a quick BTS of the final demo with teleop working (+ a small victory dance 🎉)

[Alicja Ziarko @ZiarkoAlicja]

Can complex reasoning emerge directly from learned representations? In our new work, we study representations that capture both perceptual and temporal structure, enabling agents to reason without explicit planning. https://t.co/gGdnAUixcv

[Ilya Zisman @suessmannn]

@m_bortkiewicz @ZiarkoAlicja Alicja and Michał, a great paper and a clever idea! It was a joy to read

[Aaron Wetzler @aaronwetzler]

Enabling useful teleoperation for complex dexterous robotic arm tasks in decent working spaces proved challenging with the open source SO100 design ($100 arms). Reach, degrees of freedom, and strength were insufficient. The next price point ($1000) felt unnecessary. We’ve been customizing low-cost arms ($300) for useful dexterous manipulation. Despite some challenges the teleop results are now really promising. Maybe $200-300 is the sweet spot. Curious about others’ experiences.

[Ilya Zisman @suessmannn]

@aaronwetzler wow that's something I see for the first time on twitter with such money/value tradeoff

[Ilya Zisman @suessmannn]

@gabriberton @sainingxie can you share a link to this talk, please?

[Jay Yang @Jayyanginspires]

As boring as it sounds, I’m slowly realizing that 90% of success is doing the obvious thing for a painfully long amount of time without convincing yourself you’re smarter than you are.

[Ilya Zisman @suessmannn]

@aliuahma i'll be having nightmares tonight...

[Ilya Zisman @suessmannn]

@ChrisBuilds11 @how_uhh @LeRobotHF yeah, I'd like to fix it for new calibration as soon as I have some spare time, busy with my phd now...

[Ilya Zisman @suessmannn]

Had a blast together with @how_uhh at @LeRobotHF hackathon this weekend. Built phone-based teleoperation for my SO-100 arm using pose estimation. Here’s a quick BTS of the final demo with teleop working (+ a small victory dance 🎉)

[Ilya Zisman @suessmannn]

awesome! for the better world

[Tom Silver @tomssilver]

I know 2 min is forever for social media, but check out this video. Benjamin feeds himself a whole meal with FEAST---something he is not otherwise able to do. Very proud to be part of this project led by the legendary @rkjenamani

[Ilya Zisman @suessmannn]

@Beeg_Brain @LeRobotHF I see now that it is indeed 6 dof, my brain's playing tricks on me hehehe. Thanks!