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
98 results for “keyword:"lean"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LogicKAN: Alternating Differentiable Rule Learning and Structural Repair for Compact Boolean Program Induction▼1.2k1.67
[PDF]Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning▲3.7k2.60
[PDF]Logic-Native Transformer: Mapping Transformer Computations to Trainable Logic Gate Networks▲6.6k3.33
[PDF]Improving the generalization capabilities of equivariant message passing neural networks for binding affinity prediction▼1.2k1.67
[PDF]ABRL: A Source-Aligned Lean 4 Proof Atlas for Bandit and Reinforcement Learning Theory▼4.5k2.67
[PDF]AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness▲9.2k2.67
[PDF]Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction▲4012.67
[PDF]Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean▲3.0k2.33
[PDF]NF-Bridge: Faithfully Bridging Natural and Formal Languages for Mathematical Reasoning▼1.3k1.75
[PDF]CCCV: Cross-Client Consistency Verification for High-Precision Backdoor Defense in Vertical Federated Learning▲3.0k2.33
[PDF]At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier▼4.3k2.00
[PDF]AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions▲1.7k3.33
Withdrawn or desk rejected (20)
[PDF]Foreign Exchange and Proof Diversity: Which Failures to Borrow and Which Retries to BuyDesk rejected