VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment

• URL: http://arxiv.org/abs/2605.21130v1
• Date: Wed, 20 May 2026 13:03:17 GMT
• Title: VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment
• Abstract summary: We propose textbfVersusQ, a pairwise margin reasoning framework driven entirely by direct comparisons.<n>VersusQ achieves state-of-the-art performance, strong cross-domain generalization, and reliable fine-grained ranking under heterogeneous evaluation scenarios.
• Score: 13.042805531605893
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Multimodal Models (LMMs) have shown promise for video quality assessment, but most methods still predict an absolute score for each video. Such pointwise supervision often mixes perceptual quality with dataset-specific calibration, including annotation protocols, rating habits, and score distributions. As a result, the learned scoring rule may work well within a benchmark but transfer poorly across unseen domains. We argue that relative comparisons alleviate the absolute-scale calibration bias by focusing purely on perceptual differences rather than dataset-specific rating habits. Consequently, we propose \textbf{VersusQ}, a pairwise margin reasoning framework driven entirely by direct comparisons. Specifically, VersusQ performs LMM-based comparison between two videos, reasons about their visual and temporal quality differences, and predicts a signed continuous margin that captures both the preferred choice and the degree of difference. Furthermore, to align interpretable comparison rationales with fine-grained numerical differences, we introduce Margin-Coupled GRPO, which jointly optimizes rollout-based relational reasoning and continuous margin regression. Extensive experiments on multiple public VQA benchmarks demonstrate that VersusQ achieves state-of-the-art performance, strong cross-domain generalization, and reliable fine-grained ranking under heterogeneous evaluation scenarios.

Related papers

• When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs [44.00626308821981]
  We show that comparisons are confounded by differences in model accuracy.<n>For fairer cross-model comparison, we propose ACE, an accuracy-controlled evaluation framework.
  arXiv  Detail & Related papers  (2026-06-29T18:37:48Z)
• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging [95.02210956333374]
  We propose a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation.<n>On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy.
  arXiv  Detail & Related papers  (2026-05-19T10:59:19Z)
• Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals [18.612081365101464]
  We develop a framework that combines standard labeled outcomes with pairwise comparison signals obtained by having models judge auxiliary reasoning chains.<n>Across simulations, our one-step estimator substantially improves ranking accuracy with gains increasing as model output noise grows.<n>Experiments on GPQA Diamond, AIME 2025 and GSM8K further demonstrate more precise performance estimation and more reliable model rankings.
  arXiv  Detail & Related papers  (2026-02-03T03:40:01Z)
• GRCF: Two-Stage Groupwise Ranking and Calibration Framework for Multimodal Sentiment Analysis [20.77940776708036]
  Pairwise ordinal learning frameworks capture relative order by learning from comparisons.<n>They assign uniform importance to all comparisons, failing to adaptively focus on hard-to-rank samples.<n>We propose a Two-Stage Group-wise Ranking and Framework (GRCF) that adapts the philosophy of Group Relative Policy Optimization.<n>GRCF achieves state-of-the-art performance on core regression benchmarks, while also showing strong generalizability in classification tasks.
  arXiv  Detail & Related papers  (2026-01-14T16:26:44Z)
• The Flaw of Averages: Quantifying Uniformity of Performance on Benchmarks [32.00464870277127]
  We study benchmark reliability from a distributional perspective and introduce benchmark harmony.<n>High harmony is a desirable benchmark property, indicating that the aggregate metric reflects uniform competence across models.<n>By recommending that harmony should be reported alongside accuracy, we reframe evaluation from simple performance averages to a more robust, distributionally reliable measurement of performance.
  arXiv  Detail & Related papers  (2025-09-30T02:14:30Z)
• PairBench: Are Vision-Language Models Reliable at Comparing What They See? [16.49586486795478]
  We present PairBench, a framework to evaluate large vision language models (VLMs) for automatic evaluation depending on the task.<n>Our approach introduces four key metrics for reliable comparison: alignment with human annotations, consistency across pair ordering, distribution smoothness, and controllability through prompting.<n>Our analysis reveals that no model consistently excels across all metrics, with each demonstrating distinct strengths and weaknesses.
  arXiv  Detail & Related papers  (2025-02-21T04:53:11Z)
• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
  Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date.<n>We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models.<n>Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
  arXiv  Detail & Related papers  (2024-10-04T04:56:11Z)
• Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare [99.57567498494448]
  We introduce Compare2Score, an all-around LMM-based no-reference IQA model. During training, we generate scaled-up comparative instructions by comparing images from the same IQA dataset. Experiments on nine IQA datasets validate that the Compare2Score effectively bridges text-defined comparative levels during training.
  arXiv  Detail & Related papers  (2024-05-29T17:26:09Z)
• Towards Open-ended Visual Quality Comparison [87.45004129101089]
  We extend the edge of emerging large multi-modality models (LMMs) to advance visual quality comparison into open-ended settings. Co-Instruct is a first-of-its-kind open-source open-ended visual quality comparer. We demonstrate that Co-Instruct achieves in average 30% higher accuracy than state-of-the-art open-source LMMs.
  arXiv  Detail & Related papers  (2024-02-26T15:10:56Z)
• Statistical Comparisons of Classifiers by Generalized Stochastic Dominance [0.0]
  There is still no consensus on how to compare classifiers over multiple data sets with respect to several criteria. In this paper, we add a fresh view to the vivid debate by adopting recent developments in decision theory. We show that our framework ranks classifiers by a generalized concept of dominance, which powerfully circumvents the cumbersome, and often even self-contradictory, reliance on aggregates.
  arXiv  Detail & Related papers  (2022-09-05T09:28:15Z)
• Group-aware Contrastive Regression for Action Quality Assessment [85.43203180953076]
  We show that the relations among videos can provide important clues for more accurate action quality assessment. Our approach outperforms previous methods by a large margin and establishes new state-of-the-art on all three benchmarks.
  arXiv  Detail & Related papers  (2021-08-17T17:59:39Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.