banner
LightNews
malper.bsky.social
Morris Alper
@malper.bsky.social
1K followers 650 following 54 posts
PhD student researching multimodal learning (language, vision, ...). Also a linguistics enthusiast. morrisalp.github.io
Posts Media Videos Starter Packs
malper.bsky.social
Morris Alper @malper.bsky.social · 7m
As a conlanger myself, I was mainly curious to explore whether LLMs could be used as a creative assistant for humans, as well as procedural generation in games with unbounded worlds. I hope this gets more people interested in conlanging and experimenting themselves.
malper.bsky.social
Morris Alper @malper.bsky.social · 1h
Thanks for the heads-up, fixing this.
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
Try out some of the newest languages on our project page:
conlangcrafter.github.io
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
A fully automated system for constructing languages using large language models. Our multi-stage pipeline creates coherent, diverse artificial languages with their own phonology, grammar, lexicon, and...
conlangcrafter.github.io
1 1 8
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
ConlangCrafter could potentially be used in pedagogy, typological and NLP work, and many entertainment applications. Imagine a video game where aliens can speak countless new procedurally-generated languages.
1 5
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
To enhance consistency and diversity, our pipeline incorporates randomness injection and self-refinement mechanisms. This is measured by our novel evaluation framework, providing rigorous evaluation for the new task of computational conlanging.
1 4
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
The ConlangCrafter pipeline harnesses an LLM to generate a description of a constructed language and self refines it in the process. We decompose language creation into phonology, grammar, and lexicon, and then translate sentences while constructing new needed grammar points.
1 5
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
Conlangs (Constructed Languages), from Tolkien’s Elvish to Esperanto, have long been created for artistic, philosophical, or practical purposes.
As generative AI proves its creative power, we ask:
Can it also take on the laborious art of conlang creation?
2 5
malper.bsky.social
Morris Alper @malper.bsky.social · 13h
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. 🧵👇
2 9 22
malper.bsky.social
Morris Alper @malper.bsky.social · 23d
Now accepted to #NeurIPS2025!
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
💥New preprint! WildCAT3D uses tourist photos in-the-wild as supervision to learn to generate novel, consistent views of scenes like the one shown below. h/t Tom Monnier and all collaborators (1/5)
4
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
Check out our project page and paper for more info:
Project page: wildcat3d.github.io
Paper: arxiv.org/abs/2506.13030
(5/5)
WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild
We present a framework for generating novel views of scenes learned from diverse 2D scene image data captured in the wild.
wildcat3d.github.io
2
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
At inference time, we inject the appearance of the observed view to get consistent novel views. This also enables cool applications like appearance-conditioned NVS! (4/5)
1
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
To learn from this data, we use a novel multi-view diffusion architecture adapted from CAT3D, modeling appearance variations with a bottleneck encoder applied to VAE latents and disambiguating scene scale via warping. (3/5)
1
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
Photos like the ones below differ in global appearance (day vs. night, lighting), aspect ratio, and even weather. But they give clues to how scenes are build in 3D. (2/5)
1
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 17
💥New preprint! WildCAT3D uses tourist photos in-the-wild as supervision to learn to generate novel, consistent views of scenes like the one shown below. h/t Tom Monnier and all collaborators (1/5)
1 5
malper.bsky.social
Morris Alper @malper.bsky.social · Jun 13
Disappointing that arXiv doesn't allow XeLaTex/LuaLaTex submissions, which have the least broken multilingual support of LaTeX compilers. The web shouldn't be limited to English in 2025!
malper.bsky.social
Morris Alper @malper.bsky.social · Mar 31
More coverage of our work on AI for ancient cuneiform! news.cornell.edu/stories/2025...
AI models make precise copies of cuneiform characters | Cornell Chronicle
Researchers from Cornell and Tel Aviv University have developed an approach to use artificial intelligence for reading the ancient tablets.
news.cornell.edu
4
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
See our paper, project page, and GitHub for more details and a full implementation!
ArXiv: arxiv.org/abs/2502.00129
Project page: tau-vailab.github.io/ProtoSnap/
GitHub: github.com/TAU-VAILab/P...
ProtoSnap: Prototype Alignment for Cuneiform Signs
The cuneiform writing system served as the medium for transmitting knowledge in the ancient Near East for a period of over three thousand years. Cuneiform signs have a complex internal structure which...
arxiv.org
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Finally we show that ProtoSnap-aligned skeletons can be used as conditions for a ControlNet model to generate synthetic OCR training data. By controlling the shapes of signs in training, we can achieve SOTA on cuneiform sign recognition. (Bottom: synthetic generated sign images)
1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Our results show that ProtoSnap effectively aligns wedge-based skeletons to scans of real cuneiform signs, with global and local refinement steps. We provide a new expert-annotated test set to quantify these results.
1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
ProtoSnap uses features from a fine-tuned diffusion model to optimize for the correct alignment between a skeleton matched with a prototype font image and a scanned sign. Perhaps surprising that image generation models can be applied to this sort of discriminative task!
1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
We tackle this by directly measuring the internal configuration of characters. Our approach ProtoSnap "snaps" a prototype (font)-based skeleton onto a scanned cuneiform sign using a multi-stage pipeline with SOTA methods from computer vision and generative AI.
1 1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Some prior work has tried to classify scans of signs categorically, but signs' shapes differ drastically in different time periods and regions making this less effective. E.g. both signs below are AN, from different eras. (Top: font prototype; bottom: scan of sign real tablet)
1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Arguably the most ancient writing system in the world (since ~3300 BCE), cuneiform inscriptions in ancient languages (e.g. Sumerian, Akkadian) are numerous but hard to read due to the complex writing system, wide variation in sign shapes, and physical nature as imprints in clay.
1
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Cuneiform at #ICLR2025! ProtoSnap finds the configuration of wedges in scanned cuneiform signs for downstream applications like OCR. A new tool for understanding the ancient world!
tau-vailab.github.io/ProtoSnap/
h/t Rachel Mikulinsky @ShGordin @ElorHadar and all collaborators.
🧵👇
1 1 6
malper.bsky.social
Morris Alper @malper.bsky.social · Feb 4
Our results show that ProtoSnap effectively aligns wedge-based skeletons to scans of real cuneiform signs, with global and local refinement steps. We provide a new expert-annotated test set to quantify these results.