Model Compression

LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025 Low-Bit Quantization Favors Undertrained LLMs ACL 2025 LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025 Low-Rank Interconnected Adaptation across Layers ACL 2025 LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices NAACL 2025 LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression NAACL 2025 Machine Unlearning via Simulated Oracle Matching ICLR 2025 Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning ICLR 2025 Mamba Drafters for Speculative Decoding EMNLP 2025 Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models NAACL 2025 Mask in the Mirror: Implicit Sparsification ICLR 2025 MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection ICLR 2025 Maximizing the Effectiveness of Larger BERT Models for Compression ACL 2025 MBQ: Modality-Balanced Quantization for Large Vision-Language Models CVPR 2025 MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 MELODI: Exploring Memory Compression for Long Contexts ICLR 2025 Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices EMNLP 2025 MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models ACL 2025 Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models ACL 2025 MeRino: Entropy-Driven Design for Generative Language Models on IoT Devices AAAI 2025 Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation ICML 2025 MFL-Owner: Ownership Protection for Multi-modal Federated Learning via Orthogonal Transform Watermark AAAI 2025 MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning NAACL 2025 MimicGait: A Model Agnostic Approach for Occluded Gait Recognition using Correlational Knowledge Distillation WACV 2025 Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation CVPR 2025