Knowledge Distillation

Long-tailed Adversarial Training with Self-Distillation ICLR 2025 LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models ICLR 2025 LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation ICLR 2025 LORE: Continual Logit Rewriting Fosters Faithful Generation EMNLP 2025 LoRMA: Low-Rank Multiplicative Adaptation for LLMs ACL 2025 LoSA: Long-Short-Range Adapter for Scaling End-to-End Temporal Action Localization WACV 2025 Low-Perplexity LLM-Generated Sequences and Where To Find Them ACL 2025 Low-Rank Interconnected Adaptation across Layers ACL 2025 LP-FT-LoRA: A Three-Stage PEFT Framework for Efficient Domain Adaptation in Bangla NLP Tasks AACL 2025 LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables ICCV 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 MALTO at SemEval-2025 Task 4: Dual Teachers for Unlearning Sensitive Content in LLMs SemEval 2025 Mamba-Adaptor: State Space Model Adaptor for Visual Recognition CVPR 2025 MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba ICLR 2025 Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models ACL 2025 MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models EMNLP 2025 Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement ICLR 2025 MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling ICCV 2025 Maximizing the Effectiveness of Larger BERT Models for Compression ACL 2025 Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets ICLR 2025 Membership and Memorization in LLM Knowledge Distillation EMNLP 2025 MemDistill: Distilling LiDAR Knowledge into Memory for Camera-Only 3D Object Detection ICCV 2025 Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation ACL 2025 MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities AAAI 2025