Knowledge Distillation

Teacher-Free Knowledge Distillation for Improving Short-Utterance Spoken Language Identification Interspeech 2025 Teach Small Models to Reason by Curriculum Distillation EMNLP 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 Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection AAAI 2025 The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding? 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 ToDi: Token-wise Distillation via Fine-Grained Divergence Control EMNLP 2025 Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction EMNLP 2025 Towards General-Domain Word Sense Disambiguation: Distilling Large Language Model into Compact Disambiguator EMNLP 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 ToW: Thoughts of Words Improve Reasoning in Large Language Models NAACL 2025 Tracr-Injection: Distilling Algorithms into Pre-trained Language Models ACL 2025 Unified Text and Speaker Verification using SSL model for Text-Dependent Speaker Verification Interspeech 2025 Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation ACL 2025 Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging ACL 2025 UvA-MT’s Participation in the WMT25 General Translation Shared Task EMNLP 2025 Vicomtech@WMT 2025: Evolutionary Model Compression for Machine Translation EMNLP 2025 V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models ICCV 2025 VL2Lite: Task-Specific Knowledge Distillation from Large Vision-Language Models to Lightweight Networks CVPR 2025 VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning CVPR 2025 VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion AAAI 2025 VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models CVPR 2025 VoCo-LLaMA: Towards Vision Compression with Large Language Models CVPR 2025