Assistant professor of computer science at @univmiami. My research is at the intersection of multimodal machine learning and linguistics.
🌎
Joined May 2017
- Tweets598
- Following986
- Followers487
- Likes2K
Pinned Tweet
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. 🧵👇
Morris Alper retweeted
Yes, exactly. The result is that papers that make it through are very defensively written so it can deal with all the possible objections. Possible through a slop auto research loop.
These are not nice papers for humans to read!
Morris Alper retweeted
NeurIPS 2026 Spotlight! 🌟 Physics simulators like MuJoCo MJX are changing robotics. But for studying the sensorimotor learning of speech, there's no equivalent. We built diffTLM, a differentiable vocal tract simulator, to help close that gap. (1/6)
Morris Alper retweeted
Introducing HalachaBench: we gave AI programs from the makers of ChatGPT, Claude, Gemini and others real semicha exam questions from Israel's Chief Rabbinate, in Hebrew, with no books and no internet.
The best scored 80 out of 100. Many scored under 11. 🧵
Morris Alper retweeted
𝑱𝙪𝒔𝙩 𝙥𝒖𝙗𝒍𝙞𝒔𝙝𝒆𝙙! The 1st of 6 volumes:
𝐷𝑖𝑐𝑡𝑖𝑜𝑛𝑎𝑟𝑦 𝑜𝑓 𝑡ℎ𝑒 𝐼𝑛𝑠𝑐𝑟𝑖𝑝𝑡𝑖𝑜𝑛𝑠 𝑜𝑓 𝐴𝑛𝑐𝑖𝑒𝑛𝑡 𝑁𝑜𝑟𝑡ℎ 𝐴𝑟𝑎𝑏𝑖𝑎
Open Access at this link: tinyurl.com/5n7ht4nj.
Nearly 2000 words, with citations and etymological commentary. More soon!
Very interesting taxonomy of LLM writing tics!
I'm not sure how exhaustive this is but it definitely includes some points that rub me the wrong way in LLM slop writing...
We collected matched responses from a range of frontier, near-frontier, and pre-frontier models in chat, agentic coding, and essay-writing settings, ranging from Llama-base to Claude Fable 5 and GPT-5.6 Sol.
1
2
264
🎉 Accepted to #ArabicNLP2026! Led by @BenThereDonDhat.
Levantine Arabic (LA) is diverse and under-resourced for speech technology. Our new benchmark SHAMS is designed to spur progress in tech for LA across its regional varieties! Details below. @_ArabicNLP
Key findings:
• Levantine-aware systems beat MSA-trained ones, regardless of size
• Even the best ASR model gets ~1 in 4 words wrong (>27% WER)
• Pronunciation is hardest: audio-to-phoneme is >20% CER
1
1
96
These results results highlight recent progress in LLMs and dialect-aware models as well as remaining gaps in LA speech tech. More details:
📄 Paper: arxiv.org/abs/2610.01427
🌐 Project page: shams-nlp.github.io
📁 Dataset: huggingface.co/datasets/sham…
2
65
Morris Alper retweeted
2 sentences in 20 Mayan languages.
youtu.be/urBa56k_uDo?si=BXlr…
Thrilled that we were selected among this year's @schmidtsciences Humanities and AI Virtual Institute (HAVI) grantees! 🎉🥳
"Tracing the Signs: Multimodal Foundation Models for Ancient Writing"
Looking forward to developing AI for ancient writing systems!
schmidtsciences.org/havi-202…
Check out our new paper! Speech models struggle to mix sounds from different languages -- we discover mechinterp reasons for this and find a fix!
(1/7)📢 New paper! Speech AI is getting better at hearing and speaking many languages. But what if the input mixes two languages, or is in one the model never learned? It guesses one language it knows and imposes that language's sounds on everything.
We find why, and fix it 🧵
10
260
Morris Alper retweeted
Sadly this continues to be relevant:
kalzumeus.com/2010/06/17/fal…
Great summary that mostly aligns with my own thoughts on this.
It's too bad that AI slop writing is eroding our trust in good-faith communication.
My inbox is being flooded with fully AI-generated emails from prospective students. I tried to work out why I can't bring myself to read them, and ended up with some thoughts and advice for writing cold emails in the age of AI.
My new post:
blekhman.substack.com/p/why-…
2
264
Awesome to get a warm welcome at UM!
as.miami.edu/news-and-events…
5
281
Just arrived in Sydney! Happy to connect with anyone working on speech-language tech for low-resource languages or beyond. Hit me up if you’d like to get coffee.
Heading to Sydney for Interspeech 2026 to present our work Phonikud on Hebrew G2P and TTS! 🇦🇺
If you are attending, come say hi! I will present on Tuesday - Area 7, Poster 4, paper 604.
1
8
483
Heading to Sydney for Interspeech 2026 to present our work Phonikud on Hebrew G2P and TTS! 🇦🇺
If you are attending, come say hi! I will present on Tuesday - Area 7, Poster 4, paper 604.
Update: CWoMP was just accepted as an oral presentation at #EMNLP2026! 🚀
Check out our work on using morpheme representations to gloss endangered languages! I also think this could have interesting extensions to other domains with sequence data.
Accepted to #EMNLP2026 main! 🎉
Interlinear glossed text (IGT) is standard for documenting endangered languages, but it is laborious to produce by hand.
CWoMP uses contrastively learned morpheme representations for interpretable, efficient, retrieval-based glossing!
🧵👇
