4 papers
LLMs versus the Halting Problem: Characterizing Program Termination Reasoning
Oren Sultan, Jordi Armengol-Estape, Pascal Kesseli +4
Determining whether a program terminates is a central problem in computer science. Turing's Halting Problem established termination as undecidable, showing that no algorithm can un…
A Neuro-Symbolic Approach for Reliable Proof Generation with LLMs: A Case Study in Euclidean Geometry
Oren Sultan, Eitan Stern, Dafna Shahaf
Large language models (LLMs) struggle with formal domains that require rigorous logical deduction and symbolic reasoning, such as mathematical proof generation. We propose a neuro-…
CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…
Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications
Oren Sultan, Alex Khasin, Guy Shiran +2
We present a practical distillation approach to fine-tune LLMs for invoking tools in real-time applications. We focus on visual editing tasks; specifically, we modify images and vi…