Paper-Conference

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

An MCMC perspective on constrained sampling for language models.

Emmanuel Anaya Gonzalez
•

LOUD: Synthesizing Strongest and Weakest Specifications

This work extends the specification-synthesis framework from my previous paper to a more general setting. The earlier framework synthesized strongest properties for quantifier-free …

avatar
Kanghee Park
•

Flexible and Efficient Grammar-Constrained Decoding

Flexible and efficient grammar-constrained decoding.

avatar
Kanghee Park
•
Grammar-Aligned Decoding featured image

Grammar-Aligned Decoding

Some existing works constrain possible next tokens to ensure grammaticality of generated output. But validity alone is not enough: a decoding algorithm should also preserve the …

avatar
Kanghee Park
•
Synthesizing Specifications featured image

Synthesizing Specifications

A framework for synthesizing useful program specifications.

avatar
Kanghee Park
•

Modular System Synthesis

Modular synthesis techniques for systems.

avatar
Kanghee Park
•