Model Compression

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models ACL 2025 Pushing the Limits of BFP on Narrow Precision LLM Inference AAAI 2025 QERA: an Analytical Framework for Quantization Error Reconstruction ICLR 2025 QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead AAAI 2025 Q-Mamba: Towards more efficient Mamba models via post-training quantization ACL 2025 QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration ICML 2025 QP-SNN: Quantized and Pruned Spiking Neural Networks ICLR 2025 QSpec: Speculative Decoding with Complementary Quantization Schemes EMNLP 2025 Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025 Quamba: A Post-Training Quantization Recipe for Selective State Space Models ICLR 2025 Quantization without Tears CVPR 2025 Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs EMNLP 2025 Quantized Spike-driven Transformer ICLR 2025 Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes AAAI 2025 QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models EMNLP 2025 RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning ACL 2025 RaSA: Rank-Sharing Low-Rank Adaptation ICLR 2025 RazorAttention: Efficient KV Cache Compression Through Retrieval Heads ICLR 2025 Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills EMNLP 2025 Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information AAAI 2025 Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation EMNLP 2025 Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition AAAI 2025 ReGLA: Refining Gated Linear Attention NAACL 2025 Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA ICLR 2025 RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models EMNLP 2025