Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but existing models often produce lengthy, unstructured narratives that overlook diagnostic cues and multi-view information. We present Clinical-Knowledge Guided Disease-aware Visual–Textual Alignment for QA-Style Radiology Report Generation (CliQ-RRG), a unified two-stage framework for interpretable and clinically grounded reporting. In Stage 1, CliQ-RRG employs a Disease-aware Visual–Textual Alignment module that aligns image and text representations using predicted disease embeddings, reinforced by a Prior-Guided Attention Module (PrAM) to capture multi-view dependencies across current and prior scans. In Stage 2, GraphRAG-guided retrieval augments intermediate textual representations with graph-grounded clinical evidence, and a large language model restructures them into concise, interpretable question–answer (QA) pairs with diagnostic summaries. Experiments on two public chest X-ray benchmarks demonstrate that CliQ-RRG consistently outperforms prior methods across both lexical and clinical metrics, generating accurate and clinically coherent QA-style radiology reports. Code is available at https://github.com/chandravardhan-singh-raghaw/CliQ-RRG.

Hateful memes are difficult to detect because their harmful meaning often emerges from the interaction between image and text rather than from either modality alone. This challenge becomes more severe in multilingual settings, where memes frequently contain code-mixed language and culturally grounded references. Existing Indic hateful meme datasets lack scale, language coverage, or task diversity, and current multimodal methods often overlook cross-modal semantic divergence. We introduce IndicHM, a trilingual hateful meme benchmark containing over 15,004 manually annotated image-text pairs in English, Hindi, and Bengali, including code-mixed content, supporting both hate detection and target classification. We also propose IndicHMNet, a disagreement-centric framework that decomposes representations into shared agreement and modality-specific residual subspaces and propagates the resulting disagreement-aware signal through multimodal fusion and contrastive representation learning. The proposed framework adaptively emphasizes modality-specific semantic divergence during fusion and optimization, enabling improved modeling of complex hateful meme semantics. Experiments across all languages and tasks demonstrate consistent gains over strong multimodal and vision-language baselines.

The existing research has primarily focused on text and image-based hate speech detection, video-based approaches remain underexplored. In this work, we introduce a novel dataset, ImpliHateVid, specifically curated for implicit hate speech detection in videos. ImpliHateVid consists of 2,009 videos comprising 509 implicit hate videos, 500 explicit hate videos, and 1,000 non-hate videos, making it one of the first large-scale video datasets dedicated to implicit hate detection. We also propose a novel two-stage contrastive learning framework for hate speech detection in videos. In the first stage, we train modality-specific encoders for audio, text, and image using contrastive loss by concatenating features from the three encoders. In the second stage, we train cross-encoders using contrastive learning to refine multimodal representations. Additionally, we incorporate sentiment, emotion, and caption-based features to enhance implicit hate detection. We evaluate our method on two datasets, ImpliHateVid for implicit hate speech detection and another dataset for general hate speech detection in videos, HateMM dataset, demonstrating the effectiveness of the proposed multimodal contrastive learning for hateful content detection in videos and the significance of our dataset.