Model Compression

Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA EMNLP 2025 Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs IJCAI 2025 Mitigating Memorization in Language Models ICLR 2025 Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN ICLR 2025 MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora EMNLP 2025 Mixture Compressor for Mixture-of-Experts LLMs Gains More ICLR 2025 Mixture of Lookup Experts ICML 2025 MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization EMNLP 2025 MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines EMNLP 2025 MoDeGPT: Modular Decomposition for Large Language Model Compression ICLR 2025 Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts ICLR 2025 MoKA:Parameter Efficiency Fine-Tuning via Mixture of Kronecker Product Adaption COLING 2025 MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025 MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts ACL 2025 More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025 MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning COLING 2025 MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards ICLR 2025 MPPQ: Enhancing Post-Training Quantization for LLMs via Mixed Supervision, Proxy Rounding, and Pre-Searching IJCAI 2025 MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning AAAI 2025 Multi-concept Model Immunization through Differentiable Model Merging AAAI 2025 Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits ICLR 2025 Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs ICCV 2025 MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025