Deep Learning

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models ICLR 2025 SAFE: Finding Sparse and Flat Minima to Improve Pruning ICML 2025 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs EMNLP 2025 Safe, Out-of-Distribution-Adaptive MPC with Conformalized Neural Network Ensembles L4DC 2025 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025 SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025 SAFE: Spiking Neural Network-based Audio Fidelity Evaluation ACML 2025 SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL EMNLP 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025 Safety-Prioritizing Curricula for Constrained Reinforcement Learning ICLR 2025 SAFIRE: Segment Any Forged Image Region AAAI 2025 SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation ICLR 2025 SAFR: Neuron Redistribution for Interpretability NAACL 2025 SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video ICCV 2025 SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025 SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration ICLR 2025 SAIL: Sample-Centric In-Context Learning for Document Information Extraction AAAI 2025 SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining CVPR 2025 SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge Integration EMNLP 2025 SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing CVPR 2025 SALE-MLP: Structure Aware Latent Embeddings for GNN to Graph-free MLP Distillation IJCAI 2025 Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning AAAI 2025 Saliuitl: Ensemble Salience Guided Recovery of Adversarial Patches against CNNs CVPR 2025