NeuS 2025

2nd International Conference on
Neuro-symbolic Systems (NeuS)

May 28-30, 2025

University of Pennsylvania, Philadelphia, Pennsylvania, USA

Draft Program

Wednesday, May 28

08:00-09:00 Breakfast (AGH Lobby)
08:30-9:00 Welcome by Program Chairs
09:00-10:00 Keynote 1: Claire Tomlin
10:00-10:30 Coffee break
10:30-12:30 Research Paper Oral Presentations
  1. Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: A Theoretic Foundation for Neurosymbolic AI with Practical Implications
  2. Learning Subject to Constraints via Abstract Gradient Descent
  3. Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
  4. Stochastic Neural Simulation Relations for Transferring Control under Uncertainty
12:30-14:00 Lunch break
14:00-15:00 Keynote 2: Sriram Rajamani
15:00-15:30 Coffee break
15:30-17:00 Research Paper Oral Presentations
  1. Neuro-symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation
  2. Differentiable Synthesis of Behavior Tree Architectures and Execution Nodes
  3. Knowledge-Enriched Machine Learning for Tabular Data

Thursday, May 29

08:00-09:00 Breakfast (AGH Lobby)
09:00-10:30 Tutorial Paper Presentations
  1. On Supervised vs. Unsupervised Learning for First Order Hyperbolic Nonlinear PDEs: Applications to Traffic Modeling
  2. Efficient Processing of Neuro-Symbolic AI: A Tutorial and Case Study
  3. Specification-Guided Reinforcement Learning
10:30-11:00 Coffee break
11:00-12:30 Research Paper Oral Presentations
  1. Logic Gate Neural Networks are Good for Verification
  2. Learning Formal Specifications from Membership and Preference Queries
  3. Learning Minimal Neural Specifications
12:30-14:00 Lunch break
14:00-15:00 2 Minute Presentations For Each Poster
  1. Real-Time Reachability for Neurosymbolic Reinforcement Learning based Safe Autonomous Navigation
  2. L*LM: Learning Automata from Demonstrations, Examples, and Natural Language
  3. Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
  4. Neuro-Symbolic Discovery of Markov Population Processes
  5. Taylor-Model Physics-Informed Neural Networks (PINNs) for Ordinary Differential Equations
  6. PCA-DDReach: Efficient Statistical Reachability Analysis of Stochastic Dynamical Systems via Principal Component Analysis
  7. State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems
  8. Neurosymbolic Finite and Pushdown Automata: Improved Multimodal Reasoning versus Vision Language Models (VLMs)
  9. A Study of Modus Ponens in Transformer Models
  10. Modularity in Query-Based Concept Learning
  11. Formal Synthesis of Lyapunov Stability Certificates for Linear Switched Systems using ReLU Neural Networks
  12. Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
  13. Four Principles for Physically Interpretable World Models
  14. Automaton-Based Representations of Task Knowledge from Generative Language Models
  15. End-to-End Navigation with VLMs: Transforming Spatial Reasoning into Question-Answering
  16. ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning
  17. Mining Causal Signal Temporal Logic Formulas for Efficient Reinforcement Learning with Temporally Extended Tasks
  18. Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models
  19. A Challenge to Build Neuro-Symbolic Video Agents
  20. KGAccel: A Domain-Specific Reconfigurable Accelerator for Knowledge Graph Reasoning
  21. Neuro-Symbolic Behavior Trees and Their Verification
  22. Observability of Latent States in Generative AI Models
  23. Bidirectional End-to-End Framework for Transfer from Abstract Models in Non-Markovian Reinforcement Learning
15:00-15:30 Coffee break
15:30-16:30 Poster session
16:30-17:00 Business Meeting
17:00-18:00
18:00-21:00 Banquet, Hall of Flags, Houston Hall, 3417 Spruce Street

Friday, May 30

08:00-09:00 Breakfast (AGH Lobby)
09:00-10:00 Panel Discussion
10:00-10:30 Coffee break
10:30-12:30 Research Paper Oral Presentations
  1. From Road to Code: Neuro-Symbolic Program Synthesis for Autonomous Driving Scene Translation and Analysis
  2. Assured Autonomy with Neuro-Symbolic Perception
  3. Efficient Neuro-Symbolic Policy using In-Memory Computing
  4. Interpretable Imitation Learning via Generative Adversarial STL Inference and Control
12:30-14:00 Lunch break
End of Conference

Keynote 2: Sriram Rajamani

Title: Reimagining Large Scale Software Engineering with LLMs

Abstract: Over the past few years LLM-based-tools for code completion have taken the software engineering industry by storm. Tools like GitHub Copilot are used widely by engineers to improve programmer productivity. While LLMs offer significant advantages, several challenges arise with large code bases and large-scale software engineering problems. We believe that several of these challenges can be addressed by combining LLMs with techniques from static program analysis. We describe our work on building tools to solve large scale software engineering problems for very large code bases by combining LLMs together with static analysis methods and point to research opportunities in this area.

Bio: Sriram Rajamani is Corporate Vice President at Microsoft Research. Sriram is also an ACM fellow, INAE fellow, and winner of the Computer Aided Verification Award. His work has impacted both academic and industrial practice in programming languages, systems, security, and formal verification. He is currently working on reimagining the future of programming and software engineering in this era of large AI models. Sriram did his PhD in Computer Science at UC Berkeley.