UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
fields
cs.CV 5representative citing papers
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
citing papers explorer
-
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.