Tag
The author discusses the lack of intermediate representation (IR) and verifier in the deployment of AI in serious industries, using text-to-CAD as an example to illustrate the key role of unified IR and verification in the feasibility of AI solutions.
The paper introduces VGB, a process-guided sampling algorithm with probabilistic backtracking, which significantly improves coding performance on tiny 0.5B models by being robust to verifier errors.
Sign-Gated On-Policy Distillation (SG-OPD) enhances standard on-policy distillation by using a binary verifier as a trust signal for teacher supervision, improving performance on competition-level math reasoning benchmarks.
This paper studies verifier-backed committee search as inference-time boosting for reasoning language models, showing that a committee of weak reasoning models can match the performance of much stronger models on code repair tasks like SWE-bench Verified.
Introduces LoVer, an unsupervised verifier that uses logical rules (negation consistency, intra-group and inter-group consistency) to improve LLM reasoning without labeled data, achieving performance close to supervised verifiers on reasoning benchmarks.