A constrained optimization layer interleaved with flow-matching denoising enables predictive collision avoidance in VLA models, delivering 82.8% collision avoidance and 81.6% task success on SafeLIBERO with gains over single-step baselines.
N euro L ogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A neuro-symbolic framework compiles LTLf formulas to DFAs, derives differentiable satisfaction signals from DFA progression, and uses them as a logic-based regularization loss to enforce temporal constraints in autoregressive transformer RL policies while preserving competitive returns.
citing papers explorer
-
Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies
A neuro-symbolic framework compiles LTLf formulas to DFAs, derives differentiable satisfaction signals from DFA progression, and uses them as a logic-based regularization loss to enforce temporal constraints in autoregressive transformer RL policies while preserving competitive returns.