MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
Mixed citations
Multimodal rewardbench: Holistic evaluation of reward models for vision language models
Mixed citation behavior. Most common role is background (50%).
9
Pith papers citing it
Background
50% of classified citations
citation-role summary
dataset 3
background 2
method 1
citation-polarity summary
representative citing papers
QVal is a new evaluation framework that directly measures dense supervision quality via Q-alignment to a reference policy, showing simple prompting baselines outperform 21 other methods across environments and models.
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video generation models.
RewardBench 2 is a new benchmark that supplies challenging fresh human prompts for reward model evaluation, yielding lower average scores but higher correlation with downstream best-of-N sampling and RLHF training performance.
DT2IT-MRM proposes a debiased preference construction pipeline, T2I data reformulation, and iterative training to curate multimodal preference data, achieving SOTA on VL-RewardBench, Multimodal RewardBench, and MM-RLHF-RewardBench.
citing papers explorer
-
RewardBench 2: Advancing Reward Model Evaluation
RewardBench 2 is a new benchmark that supplies challenging fresh human prompts for reward model evaluation, yielding lower average scores but higher correlation with downstream best-of-N sampling and RLHF training performance.
- Reinforcement Learning from Human Feedback