Papers with Determinantal Point Process
LeCoPCR: Legal Concept-guided Prior Case Retrieval for European Court of Human Rights cases (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches overlook the underlying semantic intent in determining relevance with respect to a query case. |
| Approach: | They propose a method that generates intents in the form of legal concepts from a query case facts and then augments the query with these concepts to enhance models understanding of semantic intent. |
| Outcome: | The proposed approach generates intents in the form of legal concepts and augments the query with these concepts to enhance models understanding of semantic intent that dictates relavance. |
CrisPrune: Combining Contextual Relevance and Intrinsic Saliency for Efficient Visual Token Pruning in MLLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for visual token pruning compromise the integrity of visual understanding in pursuit of efficiency. |
| Approach: | They propose a model-agnostic method that integrates visual saliency and text relevance to reconcile efficiency with understanding by integrating visual salions and text relevant. |
| Outcome: | The proposed method outperforms state-of-the-art methods on LLaVA-NeXT . it achieves 13 decrease in FLOPs while maintaining 97% of original performance . |
Towards Visually Grounded Multimodal Summarization via Cross-Modal Transformer and Gated Attention (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal summarization often inject shallow visual features into deep models, leading to representational mismatches and weak cross-modal grounding. |
| Approach: | They propose a framework that performs text summarization and representative image selection . a deep visual processor aligns the visual encoder with the language model at corresponding depths . |
| Outcome: | The proposed framework produces more accurate, visually grounded summaries and selects more representative images. |