Knowledge Distillation

Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond CVPR 2025 Excluding the Impossible for Open Vocabulary Semantic Segmentation AAAI 2025 Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation COLING 2025 Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference AAAI 2025 Facilitating Personalized TTS for Dysarthric Speakers Using Knowledge Anchoring and Curriculum Learning Interspeech 2025 Factorized RVQ-GAN For Disentangled Speech Tokenization Interspeech 2025 FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation CVPR 2025 Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning CVPR 2025 FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation Interspeech 2025 Fed-DFA: Federated Distillation for Heterogeneous Model Fusion Through the Adversarial Lens AAAI 2025 Federated Low-Rank Adaptation for Foundation Models: A Survey IJCAI 2025 FIND: Few-Shot Anomaly Inspection with Normal-Only Multi-Modal Data ICCV 2025 Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation AAAI 2025 Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching ACL 2025 FOCUS: Towards Universal Foreground Segmentation AAAI 2025 Fraunhofer SIT at GenAI Detection Task 1: Adapter Fusion for AI-generated Text Detection COLING 2025 From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning ICCV 2025 From Schema to State: Zero-Shot Scheme-Only Dialogue State Tracking via Diverse Synthetic Dialogue and Step-by-Step Distillation EMNLP 2025 From Slow Bidirectional to Fast Autoregressive Video Diffusion Models CVPR 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method EMNLP 2025 FuseChat: Knowledge Fusion of Chat Models EMNLP 2025 Fusing Highly Specialized Language Models for Comprehensive Expertise ACL 2025 FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation ICCV 2025 GARuD: Guided Alignment of Representations using Distillation for Ultra-Low-Resource Languages IJCNLP 2025