NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
452 results for “area:"neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)"” in ICLR 2027. 108 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Interleaving and Process-Supervising Logical Reasoning with Verifiable Reasoning Structure▼4.3k2.00
[PDF]Learning State Transitions Improves Downstream Policy Learning in Geometry Theorem Proving▼13k2.00
[PDF]From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving▼1.2k1.67
[PDF]Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement▲5103.00
[PDF]FOCON: Formula-Conditioned Receiver-Aware Clause Communication Network for Parallel SAT Solving▲3952.67
[PDF]Probe and Canonicalize: Active Identification of Hidden Physical Scale for Out-of-Distribution World Models▼1361.33
[PDF]VeriBench-Infinity: Detecting Verification Hallucinations, Valid Proofs of the Wrong Program▼4.3k2.00
Withdrawn or desk rejected (108)
[PDF]NeuroFORM: Neuro-Symbolic Formalization of Legal Rules with Counterexample-Guided RefinementWithdrawn2.00
[PDF]Certified Frozen-Midpoint Neural Integrators: Original-Energy Dissipation and Second-Order Physical TimeDesk rejected1.33
[PDF]Learning Iteration Schedules, Not Inverses: Zero-Shot Amortized Neural Preconditioning for Large-Scale Linear SystemsDesk rejected