25 papers
From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding
Haoxuan Luo, Jameson Sandler, Ferdinando Fioretto
Speculative decoding is a leading technique to reduce the cost of autoregressive generation by using a small drafter to propose several tokens, which are then verified in parallel…
Learning Discrete Decisions for MIPs with Constraint-Aware Diffusion
Vincenzo Di Vito, Mehdi Taghizadeh, Deepjyoti Deka +2
This paper proposes a novel learning-based approach to approximately solve instances of mixed-integer optimization problems. These problems are computationally challenging, as they…
Simple Self-Conditioning Adaptation for Masked Diffusion Models
Michael Cardei, Huu Binh Ta, Ferdinando Fioretto
Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if a token remains masked after…
Stability-Constrained AC Optimal Power Flow--A Gaussian Process-Based Approach
Vincenzo Di Vito, Kaarthik Sundar, Ferdinando Fioretto +1
The Alternating Current Optimal Power Flow (ACOPF) problem is a core task in power system operations, aimed at determining cost-effective generation dispatch while satisfying physi…
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
Jacob K. Christopher, James E. Warner, Ferdinando Fioretto
Deep generative models provide state-of-the-art performance across a wide array of applications, with recent studies showing increasing applicability for science and engineering. D…
Constrained Diffusion for Protein Design with Hard Structural Constraints
Jacob K. Christopher, Austin Seamann, Jingyi Cui +2
Diffusion models offer a powerful means of capturing the manifold of realistic protein structures, enabling rapid design for protein engineering tasks. However, existing approaches…