arXiv:2605.10685v3 Announce Type: replace
Abstract: Mathematical formulas serve as a language through which humans communicate with nature. Discovering mathematical laws from scientific data to describe natural phenomena has been a long-standing pursu…
arXiv:2605.11679v2 Announce Type: replace
Abstract: In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competin…
arXiv:2409.02038v3 Announce Type: replace-cross
Abstract: Existing text-to-SQL benchmarks have largely been constructed from public databases with well-structured schemas and simplistic question-SQL pairs. While large language models (LLMs) excel on t…
arXiv:2502.20427v3 Announce Type: replace-cross
Abstract: Deepfakes – manipulated or forged audio and video media – pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-base…
arXiv:2605.13062v1 Announce Type: new
Abstract: Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fail to faithfully reflect…
arXiv:2603.24649v2 Announce Type: replace
Abstract: Medical imaging benchmarks often evaluate VLMs on pre-selected 2D images, slices, crops, or patches, making evaluation closer to visual recognition. Real clinical workflows impose a different burden:…
arXiv:2605.02438v2 Announce Type: replace
Abstract: Open-set supervised anomaly detection (OSAD) aims to identify unseen anomalies using limited anomalous supervision. However, existing prototype-based methods typically model normal data via a unimoda…
arXiv:2605.13108v1 Announce Type: new
Abstract: Face presentation attack detection (FacePAD) remains challenging under diverse spoofing representation, including 2D print and replay, 3D mask-based spoofing, makeup-induced appearance manipulation, and …
arXiv:2605.13111v1 Announce Type: new
Abstract: Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply…
arXiv:2605.13360v1 Announce Type: new
Abstract: There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applications where the agent needs to interact with a perso…