Knowledge Distillation

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy ACL 2026 Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models CVPR 2026 VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation CVPR 2026 What Deserves Memory: Adaptive Memory Distillation for LLM Agents ACL 2026 What Question Did You Answer? Refining Contact Center Evaluation Plans via Backward Questions ACL 2026 Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment ACL 2026 Analyzing the Importance of Blank for CTC-Based Knowledge Distillation Interspeech 2025 An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation EMNLP 2025 A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks L4DC 2025 Data-Centric Graph Condensation via Diffusion Matching ACML 2025 EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models EMNLP 2025 Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization Interspeech 2025 Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection CVPR 2025 Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis AAAI 2025 Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence ACL 2025 Implementing Retrieval Augmented Generation Technique on Unstructured and Structured Data Sources in a Call Center of a Large Financial Institution NAACL 2025 Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles Interspeech 2025 Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity ICLR 2025 Knowledge Distillation Method for Pruned RNN-T Models via Pruning Bounds Sharing and Losses Confusion Interspeech 2025 MiniPLM: Knowledge Distillation for Pre-training Language Models ICLR 2025 Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling ACL 2025 Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition Interspeech 2025 Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks AAAI 2025 Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation Interspeech 2025 Optimizing Trajectory Matching Distillation via Parameter Difference-Driven Pruning ACML 2025