Swing by the SPIGM workshop at #NeurIPS2025 @ 3:45pm to hear @cgbelem.bsky.social present our work "Semantic Probabilistic Control of LMs" (kareemahmed.com/files/papers...) for training-free steering with a bigger bang for your buck compared to sampling. Thread coming soon!

Very excited to announce the Neurosymbolic Generative Models special track at NeSy 2025! Looking forward to all your submissions!

Excited to give an oral presentation of our work "Controllable Generation via Locally Constrained Resampling" @ #NeurIPS2024 SafeGenAI TL;DR We fix greedy constrained decoding using an ad hoc LLM approximation that we tractably condition on the constraint and reweighing samples