Morris Alper

The number of languages in the world just got a lot higher! At least constructed ones. Meet ConlangCrafter - a pipeline for creating novel languages with LLMs. A Japanese-Esperanto creole? An alien cephalopod color-based language? Enter your idea and see a conlang emerge. 🧵👇

It was a pleasure to present on ConlangCrafter at MIT at this week’s workshop on Invented, Constructed, and Emergent Languages in Multi-AI Systems!

@etai_sella @EladRichardson Great work Etai! Very cool!

Do you like image editing? Don't like prompt engineering? Want to see what a giraffe-duck hybrid looks like? If you answered yes at least once, you may like our new #SIGGRAPH2026 paper: LooseRoPE, which presents a new, prompt-free way to edit images using simple visual cues 👇

Yay, finally! Introducing Vision Banana🍌 from @GoogleDeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: vision-banana.github.io (1/5)

wrote a guide on getting compute grants as a student, something I wish I did more at the beginning of my PhD. It's honestly one of the highest ROI things you can do as a student (we've gotten 100k+ gpu hrs for roughly 2 weeks of work writing). nightingal3.github.io/blog/2026/04/1…

@ninabegus Lualatex and xelatex work well but arxiv doesn’t support them.

@ninabegus ASCII bias is strong. Good luck getting IPA to render correctly in arxiv submissions…

To be fair, it only jumped a letter. (I was misled since I've seen Begûs before.) Interesting that háčeks are still a computational problem. Who's dealing with diacritics in 2026?

@BenThereDonDhat It’s giving animorphs

מאﻣין שזה יכוل לתרוم רבוت לפיוس בﻴן בﻨﻲ האدم לﻀפרדעים

Now accepted to ACL 2026! Check out our pipeline for inventing new languages with LLMs!

@pharyngealschwa What’s the etymology of שתתאח׳ה?

Baghdadi Judeo-Arabic ˁīd lǝ-fṭīġ עִיד לִפְטִיע׳ عيد لفطيغ The name Arabic-speaking Jews in Iraq used for Passover פסח šǝttāxa שִׁתְתַאחַ׳ה شتاخة The name they used for the seder night ליל הסדר

So cool! We need a version with F3.

Introducing Look Where It Matters — High-Resolution Crops Retrieval for Efficient VLMs. VLMs don't need to process full high-res images. AwaRes uses tool-calling to retrieve only the high-res regions needed to answer a given query🧵 arxiv.org/abs/2603.16932 nimrodshabtay.github.io/AwaRes/

@mmitchell_ai To be fair, this and related works are using CIFAR-type setups while I was referring to web-scale training which is more related to works like this one: …many-van-goghs-does-it-take.github.io Though that's a good point re: likely up-weighting.

If we pinpoint “idea” as “single training example”, then yes (pointers to more refs in nature.com/articles/s4159…) But beyond that: I’d guess conversational content is upweighted, or takes some other high-value form. It’s post-training to capture actual users’ conversational usage, so would be sort of silly not to treat that like gold.

Unless I’m mistaken, common versions of ChatGPT and Claude use conversations for training—meaning they can pick up ideas in unpublished work and pass them on to other users; laundering idea plagiarism and creating “scooping” dynamics without any of the people involved knowing it.

@massiviola01 Super interesting! I'm working on a task related to knowledge probing where Flux models are clearly much worse than SDXL. Seems to be consistent with what you're saying.

Repeat after me: prettier AI images make worse training data. Wait what??🤔 A recent paper tested a dozen text-to-image models from 2022 to 2025 in synth to real transfer, and the results are discouraging to say the least.

@random_walker The problem is that this creates an incentive for advisors to delay students’ graduation because they provide cheap (relatively) labor, even though a PhD student should be eligible to graduate once they have acquired the skills that the degree is supposed to teach.

At first glance this is a totally reasonable perspective. Training PhD students is a duty! But consider this — *effectively* advising a PhD student over a 5-year period is well over 1,000 hours of work, not to mention bringing in hundreds of thousands of dollars in grants. Professors will do some things for mostly altruistic reasons (peer review) but the time commitment for advising is not something that's reasonable to ask of someone without some form of compensation. So there are two options. One is to make advising a job requirement. Unfortunately this doesn't work, because the *quality* of advising is unobservable and can't be quantified by metrics, leading to a race to the bottom. The other option is the current system — advising helps advance the professor's research agenda because PhD students do most of the work, so they take on students voluntarily. Which means it's important to ask if this subtle alignment of incentives will continue despite advancing AI capabilities. Academia has many such "subtle alignments of incentives" that the system relies on in order to function — rarely articulated, poorly understood, and fragile. Maybe the advisor-advisee relationship in CS will survive the AI transition, as @sayashk predicts, but many processes and structures will surely break. Best to rethink the system now, before it's too late.

@moranynk released another multimodal banger! Check it out!

🎙️ Introducing ID-LoRA: the first open-source model to jointly generate a video with a person's appearance and voice in a single pass from just a reference image + short audio clip. No more cascaded pipelines where the audio can't follow your prompt. youtu.be/6bWcMh18K6g?si…

@neilalexanderw1 Aren’t suppletive plural verbs found in many languages of the Americas? I know Haida has them.

1/10 Pomoan languages show something interesting that has not been explored at the family level. Most (all?) have some verbs that are dedicated solely to plural subjects or agents, with (generally) an unrelated verb then being dedicated to a singular subject or agent.

@Akjarati because ä corresponds to pan-Semitic short a and ə to short i/u?

Traditional Ethiopic transcription is pretty jarring because why is <ə> used for /ɨ/ and ä used for /ə/ You have words like Geez <mäṣaḥəft> 'books' pronounced as /mətsʼahɨft/