Knowledge Distillation

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL ACL 2025 Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task EMNLP 2025 Single-Layer Distillation with Fourier Convolutions for Texture Anomaly Detection WACV 2025 Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch CVPR 2025 Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster EMNLP 2025 SMDAF: A Scalable Sidewalk Material Data Acquisition Framework with Bidirectional Cross-Modal Knowledge Distillation WACV 2025 SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation ICLR 2025 Sparse Fine-Tuning of Transformers for Generative Tasks ICCV 2025 Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs ACL 2025 SparseSegNet: A Boundary-Aware Lightweight Segmentation Architecture for Skin Lesions ACML 2025 Spatial-Temporal Knowledge Distillation for Takeaway Recommendation AAAI 2025 Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling ICLR 2025 Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications ACL 2025 SSR: Alignment-Aware Modality Connector for Speech Language Models ACL 2025 StepER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models EMNLP 2025 Structure-Aware Handwritten Text Recognition via Graph-Enhanced Cross-Modal Mutual Learning IJCAI 2025 Structure Balance and Gradient Matching-Based Signed Graph Condensation AAAI 2025 SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation EMNLP 2025 SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025 Synthetic Data is an Elegant GIFT for Continual Vision-Language Models CVPR 2025 Tackling Long-Tailed Data Challenges in Spiking Neural Networks via Heterogeneous Knowledge Distillation IJCAI 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 TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Classical Chinese Understanding ACL 2025