
Assistant professor of computer science at @univmiami. My research is at the intersection of multimodal machine learning and linguistics.
🌎
Joined May 2017
- Tweets610
- Following998
- Followers492
- 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. 🧵👇
More cool stuff being cooked up by @eaglescode and @maxmelichov!
Now we’ve got trippy articulatory singing voice synthesis in Hebrew!!
Enabled by our Renikud G2P conversion model.
Morris Alper retweeted
I built a voice mode for Claude Code.
Like a phone call: speak, listen, interrupt. No push-to-talk.
STT and TTS run locally on your Mac (Parakeet + Phonon).
One command:
/plugin install handsfree --marketplace thewh1teagle/handsfree
@bchern @GradiumAI 👇
Now accepted to EACL (Findings) 2027! 🇬🇷
Stable Diffusion can draw "Barack Obama" but put in my name and you'll get an imaginary face. Our interpretability method detects whether text-to-image models have memorized identities with only black-box access and no reference photos.
#SIGTYP is excited to launch a shared task on Collaborative Dictionary Digitization! You can learn more about it here: sigtyp.github.io/st2027-dict…
We welcome both data contributors (if you have a dictionary to digitize) and system developers (if you'd like to develop a system)!
Morris Alper retweeted
[1/6] 🔊 We release CLAP2 and LAION-Audio-XL: 365M audio clips (1.39M hours) with 707M captions, used to train five CLAP2 models from scratch.
🏆CLAP2-L reaches 53.6% on MAEB-30, the best CLAP model on the leaderboard.
arxiv.org/abs/2611.11592
New preprint! 🐳🦁🐸
Many animals vocalize to communicate, but when we capture them in the field we get noisy recordings. We create a new, lightweight biodenoising model, CallCleaner, that you can run >90x realtime on a laptop CPU! (1/3)
Our key insight is that foundation source separation models (SAM-Audio) can often isolate animal vocalizations but may confuse output streams. By indicating spans to separate with a heuristic animal VAD, we create audio pseudo-labels to distill into a small student model. (2/3)
1
9
207
Check out our project page for audio samples and comparisons! (3/3)
Project page: callcleaner.github.io
Code: github.com/morrisalp/CallCle…
Model: huggingface.co/malper/CallCl…
7
136
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...
Replying to @thomashikaru
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
288
🎉 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…























