Knowledge Distillation

L4: Mutual Learning Helps Lifelong Language Learning EMNLP 2025 Label Augmented Dataset Distillation WACV 2025 Label-Context-Dependent Internal Language Model Estimation for CTC Interspeech 2025 Large Language Model Meets Graph Neural Network in Knowledge Distillation AAAI 2025 Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning ICCV 2025 Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseudo-Label Generation AAAI 2025 Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge EMNLP 2025 Learning Few-Step Diffusion Models by Trajectory Distribution Matching ICCV 2025 Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review ACL 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025 Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation Interspeech 2025 Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence NAACL 2025 Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval AAAI 2025 LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion ICCV 2025 LLaVA-KD: A Framework of Distilling Multimodal Large Language Models ICCV 2025 LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation AAAI 2025 Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation CVPR 2025 Logic Distillation: Learning from Code Function by Function for Decision-making Tasks IJCAI 2025 LoRACLR: Contrastive Adaptation for Customization of Diffusion Models CVPR 2025 LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks COLING 2025 LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt Tuning AAAI 2025 Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings NAACL 2025 Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation ACL 2025 Maintaining Fairness in Logit-based Knowledge Distillation for Class-Incremental Learning AAAI 2025 Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning EMNLP 2025