2931 papers
STAC-MV is the first transformer-based neural multiview video compression framework that leverages geometry-aware adaptive context selection and cross-view attention to achieve significant BD-rate improvements over conventional standards across diverse camera configurations while substantially reducing encoding time.
This paper proposes a multi-stage alignment pipeline combining preference extraction, supervised fine-tuning, and Direct Preference Optimization to effectively mitigate popularity bias in LLM-based movie recommenders, achieving improved novelty and catalog coverage while maintaining competitive accuracy.
To address the generalization gap in face forgery detection caused by the conflict between transferable high-level semantics and sparse local artifacts, this paper proposes SemFusion, a framework that combines Semantic Consistency Regularization to preserve CLIP's transferable structure with Multi-level Patch Evidence learning to effectively capture and fuse localized forgery cues.
This study demonstrates that clinically grounded concept construction enhances concept bottleneck models for chest radiograph classification, with supervised approaches achieving strong performance comparable to non-bottleneck baselines while label-free models offer a promising alternative when concept annotations are unavailable.
This paper introduces BioGraph-SentiCOVID, a calibrated adaptive-context graph neural framework that optimizes conversational context selection and hyperparameters via a genetic algorithm to achieve state-of-the-art sentiment classification of noisy COVID-19 tweets on Twitter.
This paper presents a comparative study of classical, neural, and transformer models for political stance detection on X during the 2024 U.S. election, demonstrating that while fine-tuned BERTweet achieves the highest accuracy, carefully engineered classical models like linear SVMs offer a highly competitive, more efficient, and interpretable alternative for scalable deployment.
This paper demonstrates that classical community detection methods consistently match or outperform recent Graph Neural Networks on bipartite networks using only topology, based on a comprehensive evaluation of fourteen methods across eight real-world and five synthetic datasets.
This paper describes and formative-evaluates a governed, large language model-supported workflow implemented at a Colombian health-AI company to systematically improve the throughput and traceability of grant discovery and proposal development while maintaining researcher oversight. In Phase 1 ("The Treasure Hunt"), the 83 candidates are identified as post-filter selections that passed the filtering criteria and were considered suitable, rather than being rejected.
This paper proposes an iterative feedback-refinement framework using large language models to dynamically induce adaptive schemas for converting unstructured clinical notes into faithful, structured representations, which outperforms existing baselines by significantly reducing omission and hallucination without requiring labeled data or fine-tuning.
This study demonstrates that single-metric evaluations can mask the universal collapse of surgical AI models across sites by highlighting apparent robustness in specific classes, whereas dual-metric audits reveal widespread failure and that backbone substitution, in the configurations we tested, did not close the gap.