Multimodal large language models can expose task-relevant evidence through generation, but producing useful evidence does not by itself determine how it enters a retrieval embedding. We study whether the semantic organization of that evidence can also specify where representations are read. To address this question, we...
Zi-Rong Chen, Fu-Da Ye, En-Jun Du et al.· 1 citation
StepLearn is introduced, a nonparametric framework that separates immediate use from persistent trust, while requiring prospective validation before reuse across episodes, and turns informative transitions into hypotheses that can guide the next step.
RePair is introduced, guided by three principles---Validity, Minimality, and Locality---which mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective.
Si-Yi Liu, Xiao-Rong Zhu, En-Jun Du et al.· 0 citations
Large vision-language models used as listwise rerankers must jointly process visual tokens from tens of candidates per query, making token pruning essential for practical deployment. Existing pruning methods retain tokens by attention saliency, yet we show that saliency is systematically misaligned with ranking contrib...
Si-Yi Liu, Han-Jun Yang, Chen-Chen Zhang et al.· 1 citation
VIsion Pruning Router is proposed, a lightweight VIsion Pruning Router that adaptively selects the pruning strategy predicted to be best suited to each input at a specified pruning level that proves effective across various MLLM backbones and yields consistent gains on unseen benchmarks, highlighting the potential of s...
Hai-Jin Liang, P. Zhou, Zheng-Lin Wan et al.· 0 citations
This paper proposes UniRank, a Homogeneous Scaling framework that consolidates multiple ranking objectives into a single, unified generative model and introduces two paradigmatic innovations: Parallel Prediction via Task-Specific Anchors and Reinforcement Learning Optimization with Posterior CoT.
De-Zhi Ye, Junwei Hu, Xiaoyang Chen et al.· Proceedings of the 32nd ACM...· 0 citations
EviRank is recast multimodal image re-ranking as a semantic constraint satisfaction problem and proposed, which parses any query - text-only, image-only, or composed - into a unified evidence package: typed criteria across six semantic slots, each labelled required, forbidden, or ignorable.
Enjun Du, Si-Yi Liu, Zi-Rong Chen et al.· 2 citations
These findings suggest that, within the pointwise scoring paradigm, routing continuous relevance semantics through discrete text constrains ranking signal resolution reveals a bottleneck that is stable and difficult to overcome under current standard methods, rather than an easily resolvable training bias.
Xiaoyang Chen, Jie Liu, Hai-Jin Liang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
