4 papers
Rank-Aware Speculative Sampling for Diffusion Draft Trees
Marcello Bullo, Yanxiao Liu, Öykü Sıla Güner +2
Speculative sampling accelerates diffusion generation by verifying inexpensive draft states in parallel while preserving the target law. Recent tree-based methods allocate the para…
Accelerating Diffusion Sampling via Speculative Draft Trees
Marcello Bullo, Yanxiao Liu, Öykü Sıla Güner +2
Speculative sampling accelerates diffusion model generation by drafting inexpensive candidate states and correcting them under a coupling that preserves the target distribution exa…
Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality
Arpan Mukherjee, Marcello Bullo, Debabrota Basu +1
While test-time scaling with verification has shown promise in improving the performance of large language models (LLMs), the role of the verifier and its imperfections remain unde…
SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
Arpan Mukherjee, Marcello Bullo, Deniz Gündüz
Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity…