Alistaired

Researcher in Reinforcement Learning and MARL and causality at @Nanjing University

[Alistaired @Alistaired_Van]

@sangoh64166 Hi Sangooh!

Im working on Causal world models and RL at @ Nanjing University.
Nice to meet you!

[Alistaired @Alistaired_Van]

@RaniadoesBiz @GooglePlay Interesting last gig, how do you deal with automating the process and LLM call costs?

[Alistaired @Alistaired_Van]

@jueun_kim_ Hi Jueun,
I'm Rafik, AI researcher @ Nanjing University. Congrats on your paper! i have one paper at AAAI and three submissions.
I work on the intersection of RL, World models and causality. Nice to connect!

[Black Rifle Coffee @blckriflecoffee]

5am, Black Rifle Coffee consumed, Black Rifle Energy packed up, headed to the range

[Alistaired @Alistaired_Van]

@marvin1764 @EsotheticAnglo He was 5th Dan rank in Kendo and 1st Dan rank in Iaijutsu

[Alistaired @Alistaired_Van]

@floatingwordist Nice nice, Domestic Kano- ?

[WhiteRadiation @WhiteRadiation6]

Kadokawa announces 'Re:Zero Re:Told', a remake of Re:Zero Seasons 1 and 2.

"The goal with this project is to bring these prior seasons to the visual standard of Seasons 3 and 4 while adding crucial cut content back to these seasons." Producer Sho Tanaka states in an interview.

[Mengyue Yang @Mengyue_Yang_]

Very nice work! Grounding world models by existing game engine is strong way to guarantee the physical consistency.

In our recent project Oneira. https://t.co/sgSnlLOoFb. Arxiv: https://t.co/hKlzv3576t. we also explored the power of coding agents for world models, with a focus on explicit world representations.

[Moonstruck❤️‍🔥 @godspeed_aflame]

“human psychology, existentialism, and the absurdity of life”

[Total Philosophy @TotalPhilo]

Problem of induction

[scribe @nishanciefendi]

a lost world

[Alistaired @Alistaired_Van]

Concerning the recent OpenAI Math publications, I couldnt help but be reminded by this stark letter.. (I think it was written in the early 2000s)

[Xindi Yang @Madaoer_Yxd]

🌍 Introducing Oneira, an interactive video world model where a coding agent keeps an explicit world state.

Objects that appear as you explore become interactive, and your changes persist over long horizons.

Project: https://t.co/DhvJxnZb2j
Paper: https://t.co/7e4uo2Iqu2

[Alistaired @Alistaired_Van]

@shivon @ressay591 chof lmao

[Thomas Wolf @Thom_Wolf]

Karpathy: disappears from X

Ben Affleck: alright, gather round, so you'll want to freeze the base weights first, learning rate 2e-4

[Minghao Fu @Minghao__Fu]

TC-WM is accepted at #NeurIPS2026! 🎉

A generic visual representation isn’t always a good latent state for planning and control.

For control, we need more than visual fidelity. Instead, we aim for task-centric representations that reflect physical dynamics and task-relevant information, while still leveraging the scalability of visual foundation models.

Compared with DINO-WM, TC-WM learns a lower-dimensional representation with higher latent-space utilization and diversity. These improvements translate into stronger performance, especially with the clearest gains on 3D contact-rich manipulations.

Webpage: https://t.co/zlSkDowoC2
Paper: https://t.co/J1D3lnpwAa
Code: https://t.co/bgcUZ3JNQj

[Alistaired @Alistaired_Van]

ICLR doneee, TIME TO WATCH CARNIVAL PHANTASM!!

[Alistaired @Alistaired_Van]

Something to add to https://t.co/cV75XqBjnH, perhaps, would be nicee

[Mengyue Yang @Mengyue_Yang_]

We released a world model benchmark with mechanism reasoning puzzles on more than 150 tasks. The most interesting work I contributed to.

[Alistaired @Alistaired_Van]

Nishitani-san, you so real for that..

[Aya Nishitani 西谷史 @ayanakajima3]

This is my thinking. Out of the British concept known as Chaos Magic, there were some people who viewed reality through the thinking way of computer architecture. As a result, the concept of using computers as tools for magic was already being born. However, I decided to take the actual process of summoning devils and turn it into a program. I went as far as creating a flowchart for it, which I then entrusted to Akemi Nakajima.

[Aya Nishitani 西谷史 @ayanakajima3]

I was asked, "How did you come up with the idea of summoning devils into a computer?"However, back in 1985 when I wrote Megami Tensei, the similarities between computer theory and magical theory were already being discussed on BBS networks and in magazines. It was a popular thinking thought among the otaku of that era, and I resonated with it deeply. To be a bit more specific...