Showing 1–20 of 21 results
/ Date/ Name
Oct 21, 2024Conflict-Aware Adversarial TrainingNov 22, 2025SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent SystemMar 12, 2026Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety AlignmentJan 24, 2026Covariate-assisted Grade of Membership Models via Shared Latent GeometryFeb 13, 2024Glass Segmentation with Multi Scales and Primary Prediction GuidingJun 8, 2025Enhancing the Safety of Medical Vision-Language Models by Synthetic DemonstrationsSep 8, 2020Region Comparison Network for Interpretable Few-shot Image ClassificationDec 13, 2024No Free Lunch for Defending Against Prefilling Attack by In-Context LearningMay 21, 2025EPBench: A Benchmark for Short-term Earthquake Prediction with Neural NetworksMay 19, 2024NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot SegmentationOct 26, 2023PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient DescentDec 7, 2025Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought LengthDec 5, 2024Beyond Asymptotics: Practical Insights into Community Detection in Complex NetworksOct 30, 2024Smaller Large Language Models Can Do Moral Self-CorrectionOct 8, 2025On the Convergence of Moral Self-Correction in Large Language ModelsJun 6, 2024Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and ForgetfulnessOct 16, 2024Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language ModelsMar 16, 2026Scalable Text-Embedding-informed Cognitive Diagnosis of Large Language ModelsMar 19, 2026Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language ModelsJun 4, 2024On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept