[1/2] We've released the code for LegoGPT. Our autoregressive model generates physically stable and buildable designs from text prompts by integrating physics laws and assembly constraints into LLM training and inference.

Code: github.com/AvaLovelace1...
Website: avalovelace1.github.io/LegoGPT/

NL2FOL: Translating natural language to first-order logic for logical fallacy detection. ~ Abhinav Lalwani et als. arxiv.org/abs/2405.02318 #LLMs #Logig #SMT

📝 Paper: Atom of Thoughts for Markov LLM Test-Time Scaling (arxiv.org/abs/2502.12018)
📦 Code: github.com/qixucen/atom

One of the most interesting new research in the LLM space: introducing Large Language Diffusion Models. arxiv.org/pdf/2502.09992

if you want to try a diffusion LLM, inception labs just released one. it goes 1000 tokens/sec on regular H100s, absolutely nuts how fast it is

speed alone makes these things interesting

www.inceptionlabs.ai/news

One more week until the abstract deadline 😲
As an extra motivator, we are excited to announce our amazing keynote speakers 🤩!

- Guy van den Broeck (@guyvdb.bsky.social UCLA)
- Thomas Kipf (@tkipf.bsky.social Google DeepMind)
- Deborah McGuinness (RPI)

2025.nesyconf.org

We have a 60 pager / survey / handbook on Mapping the Neuro-Symbolic AI Landscape by Architectures