Loris D'Antoni

2 accepted papers

2026

Constrained Adaptive Rejection Sampling

Paweł Parys, Sairam Vaidya, Taylor Berg-Kirkpatrick, Loris D'Antoni

ICML 2026poster

Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained generation fall along a spectrum: greedy constrained decoding methods enforce validity during decoding but distort the LM’s di…

Cited by 0 Source ↗Scholar ↗

2026

Continuous Diffusion Models Can Obey Formal Syntax

Jinwoo Kim, Taylor Berg-Kirkpatrick, Loris D'Antoni

ICML 2026poster

Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their continuous latent dynamics make discrete constraints---e.g., the output should be a JSON file that matches a given schema---difficult to impose. We introduce…

Cited by 0 Source ↗Scholar ↗

Loris D&#x27;Antoni

Constrained Adaptive Rejection Sampling

Continuous Diffusion Models Can Obey Formal Syntax

Loris D'Antoni