Verification papers, 2023–2026

Key findings

• Verification went from 8 papers in 2023 to 48 in 2026, roughly 6.0x in three years.
• NeurIPS publishes the most Verification work: 45 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with Reasoning Models: papers tagged with both rose from 0 in 2023 to 8 in 2026.
• Among the 5 topics under Security and Trust, it ranks #4 by 2026 paper count; the fastest grower in the group, Watermarking, is up 9.3x versus 6.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification
• ICML 2026Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean
• ICLR 2026Parameterized Hardness of Zonotope Containment and Neural Network Verification
• CVPR 2026Goldilocks Test Sets for Face Verification
• NeurIPS 2025Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training
• ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
• ICLR 2025Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
• CVPR 2025PHGC: Procedural Heterogeneous Graph Completion for Natural Language Task Verification in Egocentric Videos
• NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
• ICML 2024Compact Optimality Verification for Optimization Proxies
• ICLR 2024CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
• CVPR 2024Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
• NeurIPS 2023[Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”
• ICML 2023Trapdoor Normalization with Irreversible Ownership Verification
• ICLR 2023Fundamental Limits in Formal Verification of Message-Passing Neural Networks
• CVPR 2023Efficient Verification of Neural Networks Against LVM-Based Specifications
• NeurIPS 2026End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
• ICML 2026The Latent Guardian: Defending Collaborative Perception via Feature-Level Consistency Verification
• ICLR 2026Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality
• CVPR 2026Lipschitz Optimization for Formal Verification of Homographies

All Verification papers

111 papers, page 2 of 3

51. CVPR 2025Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
52. CVPR 2025Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
53. ICLR 2025Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
54. ICLR 2025Block Verification Accelerates Speculative Decoding
55. ICLR 2025Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
56. ICLR 2025Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach
57. ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
58. ICLR 2025Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA
59. ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
60. ICML 2025DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts
61. ICML 2025No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
62. ICML 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
63. ICML 2025Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
64. ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
65. ICML 2025Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
66. ICML 2025Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
67. NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
68. NeurIPS 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
69. NeurIPS 2025Compositional Neural Network Verification via Assume-Guarantee Reasoning
70. NeurIPS 2025DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian Networks
71. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution
72. NeurIPS 2025Generating and Checking DNN Verification Proofs
73. NeurIPS 2025Learning Simple Interpolants for Linear Integer Arithmetic
74. NeurIPS 2025Let a Neural Network be Your Invariant
75. NeurIPS 2025Limitations of Normalization in Attention
76. NeurIPS 2025RvLLM: LLM Runtime Verification with Domain Knowledge
77. NeurIPS 2025Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training
78. NeurIPS 2025SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
79. NeurIPS 2025Traversal Verification for Speculative Tree Decoding
80. NeurIPS 2025Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion
81. NeurIPS 2025Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification
82. CVPR 2024Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
83. ICLR 2024CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
84. ICLR 2024Expressivity of ReLU-Networks under Convex Relaxations
85. ICLR 2024Lemur: Integrating Large Language Models in Automated Program Verification
86. ICLR 2024Prediction without Preclusion: Recourse Verification with Reachable Sets
87. ICML 2024Compact Optimality Verification for Optimization Proxies
88. ICML 2024Copula-Nested Spectral Kernel Network
89. ICML 2024Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
90. ICML 2024Relational DNN Verification With Cross Executional Bound Refinement
91. ICML 2024SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
92. ICML 2024Verification of Machine Unlearning is Fragile
93. ICML 2024VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees
94. NeurIPS 2024Compact Proofs of Model Performance via Mechanistic Interpretability
95. NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
96. NeurIPS 2024FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
97. NeurIPS 2024Neural Model Checking
98. NeurIPS 2024Optimistic Verifiable Training by Controlling Hardware Nondeterminism
99. NeurIPS 2024Relational Verification Leaps Forward with RABBit
100. NeurIPS 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes

FAQ

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

111 in total: 8 in 2023, 22 in 2024, 33 in 2025, 48 in 2026.

How many Verification papers are at NeurIPS 2026?

NeurIPS 2026 has 19 Verification papers, versus 15 the year before.

How many Verification papers are at ICLR 2026?

ICLR 2026 has 14 Verification papers, versus 6 the year before.

How many Verification papers are at ICML 2026?

ICML 2026 has 12 Verification papers, versus 8 the year before.

How many Verification papers are at CVPR 2026?

CVPR 2026 has 3 Verification papers, versus 4 the year before.

Which conference publishes the most Verification papers?

NeurIPS, with 45 papers from 2023 to 2026.