arXiv subjects

Yuyin Wang

Publications and source records attributed to Yuyin Wang.

3 recordsLinked to original sources

arXiv2026

Mind the Divergence: Divergence-Guided Reliability-Aware Fusion and Adaptive LLM Prompting for Conversational Emotion Recognition

Multimodal emotion recognition in conversations (MERC) integrates textual, acoustic, and visual cues to identify utterance-level emotions. However, existing approaches generally do not explicitly adapt multimodal processing to the degree of inter-modal predictive disagreement. In real conversations, semantic incongruity, concealed emotion, noisy observations, and ambiguity can affect modality-specific emotional evidence differently, while the reliability of individual modalities varies across samples. Rather than identifying each source of inconsistency separately, we model their common consequence for emotion recognition as predictive disagreement among unimodal emotion distributions over the same emotion-label set. Such disagreement makes indiscriminate fusion prone to propagating unreliable or competing evidence. Inspired by the Brunswik Lens Model, we propose MiD-ERC, a divergence-centric framework that quantifies inter-modal predictive disagreement using a normalized divergence score and estimates sample-specific modality reliability. MiD-ERC uses these signals to coordinate divergence-guided cross-modal gating, divergence-modulated reliability weighting, and divergence-conditioned adaptive LLM prompting. The framework is trained end-to-end using only standard emotion annotations, without requiring additional conflict labels, auxiliary data construction, or external retrieval modules. Experiments on IEMOCAP and MELD demonstrate that MiD-ERC achieves state-of-the-art performance, with particularly pronounced improvements on high-divergence samples.

cs.AI↗

arXiv2026

CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization

Recent advances in pre-training vision-language models (VLMs), e.g., contrastive language-image pre-training (CLIP) methods, have shown great potential in learning out-of-distribution (OOD) representations. Despite showing competitive performance, the prompt-based CLIP methods still suffer from: i) inaccurate text descriptions, which leads to degraded accuracy and robustness, and poses a challenge for zero-shot CLIP methods. ii) limited vision-language embedding alignment, which is one important factor affecting generalization performance. To tackle the above issues, this paper proposes a novel Conditional Domain prompt Learning (CoDoL) method, which utilizes readily-available domain information to form prompts and contributes to improved vision-language embedding alignment, which we identify as one factor underlying the observed OOD generalization gains. To capture both instance-specific and domain-specific information, we further propose a lightweight Domain Meta Network (DMN) to generate input-conditional tokens for images in each domain. Extensive experiments on four OOD benchmarks (PACS, VLCS, OfficeHome, and DigitDG) validate the effectiveness of our proposed CoDoL method in terms of empirically improves vision-language embedding alignment across four DG benchmarks, which we present as a contributing factor (rather than the sole cause) of the observed OOD gains.

cs.CV↗

arXiv2025

Axial Behaviour of Pre-Damaged RC Short Columns Retrofitted with Square Corrugated Steel Jackets

This study proposes a strengthening method employing square corrugated steel jackets as external confinement, which significantly enhances both the bearing capacity and ductility of existing reinforced concrete (RC) columns. Axial compression tests were conducted on ten short column specimens to evaluate the effects of corrugated steel thickness (1.6, 2.0, and 2.7 mm), preloading level before jacketing (40%, 60%, and 100% of the original capacity), and connection type (welding vs. bolting). A computational model was developed to predict the ultimate bearing capacity of the strengthened sections. The main findings are as follows: (1) The corrugated steel jackets increased the ultimate bearing capacity of the existing RC columns by 34.6% to 67.3%. (2) Given the relatively low confinement efficiency in square sections, thinner corrugated steel plates can be used in a material-efficient manner to achieve comparable strengthening effects. (3) Fully welded connections between corrugated plates induce less stress concentration and provide better transverse confinement effectiveness compared to bolted connections. (4) In a pre-unloaded column, greater existed damage causes concrete softening and increased lateral expansion under re-compression. This dilation promotes a tighter interaction between the core concrete and the outer jacket, activating stronger passive confinement after being jacketed. (5) The low longitudinal stresses in the jacket indicate that its primary role is to provide lateral confinement rather than to resist axial loads directly. (6) It is recommended to employ a calculation method that accounts for both pre-damage and confinement effects to ensure a conservative and reliable design of corrugated steel-jacketed RC columns with pre-damage.

math.NA↗