Knowledge Distillation

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models ICLR 2025 Talking Head Anime 4: Distillation for Real-Time Performance WACV 2025 TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting CVPR 2025 Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance AAAI 2025 Targeted Distillation for Sentiment Analysis EMNLP 2025 Task Vector Quantization for Memory-Efficient Model Merging ICCV 2025 TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Classical Chinese Understanding ACL 2025 Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences ACL 2025 Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student IJCNLP 2025 Teach Small Models to Reason by Curriculum Distillation EMNLP 2025 TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance ICCV 2025 Temporal reasoning for timeline summarisation in social media ACL 2025 Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks CVPR 2025 TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing EMNLP 2025 Tensor-aggregated LoRA in Federated Fine-tuning ICCV 2025 Text2Sql: Pure Fine-Tuning and Pure Knowledge Distillation NAACL 2025 Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection AAAI 2025 The Gemma Sutras: Fine-Tuning Gemma 3 for Sanskrit Sandhi Splitting EMNLP 2025 The Green KNIGHT: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformers EMNLP 2025 The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding? ACL 2025 Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances MCQ Generation and Distractor Quality ACL 2025 Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series EMNLP 2025 TinySAM: Pushing the Envelope for Efficient Segment Anything Model AAAI 2025 TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG EMNLP 2025 ToDi: Token-wise Distillation via Fine-Grained Divergence Control EMNLP 2025