ICLR 2025PastOther
ICLR 2025 Workshop: VerifAI: AI Verification in the Wild
ICLR 2025 Workshop VerifAI
- Submission deadline
- Feb 8, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (32)
Fetched from OpenReview (v2) on 2026-06-10.
ABSINT-AI: Language Models for Abstract Interpretation
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
CRANE: Reasoning with constrained LLM generation
Exact Certification of (Graph) Neural Networks Against Label Poisoning
Guided Proof Search Using Large Language Models and Lemma Extraction in Coq
LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction
Learning Automata from Demonstrations, Examples, and Natural Language
Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations
Lightweight Latent Verifiers for Efficient Meta-Generation Strategies
LipShiFT: A Certifiably Robust Shift-based Vision Transformer
LLMV-AgE: Verifying LLM-Guided Planning for Agentic Exploration in Open-World RL
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers (Abridged)
Multi-Turn Code Generation Through Single-Step Rewards
Neural Abstract Interpretation
NO STRESS NO GAIN: STRESS TESTING BASED SELF-CONSISTENCY FOR OLYMPIAD PROGRAMMING
On the Query Complexity of Verifier-Assisted Language Generation
Randomly Sampled Language Reasoning Problems Reveal Limits of LLMs
ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Format Restriction, and Column Exploration
Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
Scaling Randomized Smoothing to state-of-the-art Vision-Language Models
Scaling Test-Time Compute Without Verification or RL is Suboptimal
Self-Steering Language Models
Synthesis and Verification of String Stable Control for Interconnected Systems via Neural sISS Certificate
Tasks, Challenges, and Paths Towards AI for Software Engineering
Temporal Consistency for LLM Reasoning Process Error Identification
Toward Trustworthy Neural Program Synthesis
Training and Verifying robust Kolmogorov-Arnold Networks
Type-Constrained Code Generation with Language Models
Using GPUs And LLMs Can Be Satisfying for Nonlinear Real Arithmetic Problems
Verifying Omega-regular Properties of Neural Network-Controlled Systems via Proof Certificates