Logic and Neural papers, 2023–2026

Key findings

• Logic and Neural fell from 162 papers in 2023 to 86 in 2026, so interest is cooling.
• NeurIPS publishes the most Logic and Neural work: 173 papers from 2023 to 2026, 47% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 1 in 2023 to 8 in 2026.
• Among the 5 topics under Neurosymbolic AI, it ranks #2 by 2026 paper count; the fastest grower in the group, Mathematical Reasoning, is up 10x versus 0.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints
• ICML 2026Length Generalization Bounds for Transformers
• ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
• CVPR 2026Med-CMR A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic
• NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
• ICML 2025Counterfactual Graphical Models: Constraints and Inference
• ICLR 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints
• CVPR 2025Learning Affine Correspondences by Integrating Geometric Constraints
• NeurIPS 2024Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
• ICML 2024A Field Guide for Pacing Budget and ROS Constraints
• ICLR 2024LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
• CVPR 2024MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
• NeurIPS 2023Aligning Gradient and Hessian for Neural Signed Distance Function
• ICML 2023Eventual Discounting Temporal Logic Counterfactual Experience Replay
• ICLR 2023Global Explainability of GNNs via Logic Combination of Learned Concepts
• CVPR 2023Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model
• NeurIPS 2026Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
• ICML 2026KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
• ICLR 2026The Logical Expressiveness of Topological Neural Networks
• CVPR 2026NeuroRule Bridging Vision and Logic with Differentiable Rule Induction

All Logic and Neural papers

20 papers, page 1 of 1

1. ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
2. ICLR 2026Automating the Refinement of Reinforcement Learning Specifications
3. ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
4. ICLR 2026Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
5. ICLR 2026Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: from $2$ Bits to $k$ Bits
6. ICLR 2026Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
7. ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
8. ICLR 2026Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies
9. ICLR 2026HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
10. ICLR 2026Hot Fuzz: Temperature-Tunable Composition of Diffusion models with Fuzzy Logic
11. ICLR 2026Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample
12. ICLR 2026Light Differentiable Logic Gate Networks
13. ICLR 2026Near-Optimal Online Deployment and Routing for Streaming LLMs
14. ICLR 2026On the Expressiveness of State Space Models via Temporal Logics
15. ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
16. ICLR 2026Probability Distributions Computed by Autoregressive Transformers
17. ICLR 2026Sharing State Between Prompts and Programs
18. ICLR 2026The Logical Expressiveness of Topological Neural Networks
19. ICLR 2026Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework
20. ICLR 2026Transformers are Inherently Succinct

FAQ

How many Logic and Neural papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

366 in total: 162 in 2023, 64 in 2024, 54 in 2025, 86 in 2026.

How many Logic and Neural papers are at NeurIPS 2026?

NeurIPS 2026 has 32 Logic and Neural papers, versus 23 the year before.

How many Logic and Neural papers are at ICLR 2026?

ICLR 2026 has 20 Logic and Neural papers, versus 11 the year before.

How many Logic and Neural papers are at ICML 2026?

ICML 2026 has 25 Logic and Neural papers, versus 12 the year before.

How many Logic and Neural papers are at CVPR 2026?

CVPR 2026 has 9 Logic and Neural papers, versus 8 the year before.

Which conference publishes the most Logic and Neural papers?

NeurIPS, with 173 papers from 2023 to 2026.