Deep Learning

MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES ICML 2025 Mitigating Overfitting During Speech Foundation Model Fine-tuning: Applications to Dysarthric Speech Detection Interspeech 2025 Mitigating Over-Smoothing in Graph Neural Networks via Separation Coefficient-Guided Adaptive Graph Structure Adjustment IJCAI 2025 Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification ICML 2025 Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning ICLR 2025 Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversion ACL 2025 Mitigating Pervasive Modality Absence Through Multimodal Generalization and Refinement AAAI 2025 Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding ACL 2025 Mitigating Selection Bias with Node Pruning and Auxiliary Options ACL 2025 Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025 Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework AAAI 2025 Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach Interspeech 2025 Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning ACL 2025 Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent EMNLP 2025 MITracker: Multi-View Integration for Visual Object Tracking CVPR 2025 MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025 MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation ICCV 2025 MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective ICCV 2025 MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges ICML 2025 MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations WACV 2025 Mixed-Curvature Multi-Modal Knowledge Graph Completion AAAI 2025 MixerMDM: Learnable Composition of Human Motion Diffusion Models CVPR 2025 Mixing Inference-time Experts for Enhancing LLM Reasoning EMNLP 2025 MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora EMNLP 2025 Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection AAAI 2025