The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

This paper proposes a unified evaluation framework for hate speech detection that systematically assesses model performance and explainability across various label and rationale representation spaces,…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness b…

The paper introduces Multi-Response Training (MRT) to combat the 'mode lottery' problem in language model fine-tuning, showing that retaining multiple valid responses significantly improves distributi…

The paper proposes a Bayesian Spectral Emotion Transition Discovery (BSETD) framework to model emotion transitions using multi-annotator soft labels, successfully recovering distinct affective transit…

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…

Sympatheia is a speech-to-speech dialogue framework that generates emotionally adaptive responses by conditioning its output on continuous affect signals derived from user speech or external multimoda…

The paper addresses Perceptual Judgment Bias in multimodal LLM judges by introducing a new dataset and a unified training framework that forces models to prioritize visual evidence over plausible text…

The paper proposes Sensitivity-Uncertainty Alignment (SUA), a framework that measures the misalignment between a model's prediction instability and its stated uncertainty to improve model reliability.

The paper proposes UF-AMA, a unified framework that achieves state-of-the-art cross-domain emotion recognition by adaptively aligning and fusing multimodal physiological signals like EEG and eye-track…

The paper proposes a Variational Adapter (VACSR) to improve cross-modal similarity representation by treating fine-grained image-text matching as a variational inference problem, thereby mitigating th…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

The paper proposes a novel multimodal framework for session-based music recommendation that jointly models audio, lyric, and semantic content signals within a unified LLM-based sequential reasoning sy…