VRCD prioritizes visually complementary positions during parallel decoding in dMLLMs by measuring attention overlap with the new Visual Redundancy Index, yielding accuracy gains over confidence-based baselines on M^3CoT and MMBench.
Optimizing decoding paths in masked diffusion models by quantifying uncertainty.arXiv preprint arXiv:2512.21336, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
OALMs exhibit order-dependent likelihoods up to 0.49 nats/token and a uniform confidence spread maximizes recoverability, motivating Var(log q_t) as a decoding diagnostic.
citing papers explorer
-
Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
VRCD prioritizes visually complementary positions during parallel decoding in dMLLMs by measuring attention overlap with the new Visual Redundancy Index, yielding accuracy gains over confidence-based baselines on M^3CoT and MMBench.
-
Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading
OALMs exhibit order-dependent likelihoods up to 0.49 nats/token and a uniform confidence spread maximizes recoverability, motivating Var(log q_t) as a decoding diagnostic.
- Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning