Model Compression

FloE: On-the-Fly MoE Inference on Memory-constrained GPU ICML 2025 FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference EMNLP 2025 Forget the Data and Fine-Tuning! Just Fold the Network to Compress ICLR 2025 Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation ICCV 2025 FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point ACL 2025 FREE: Fast and Robust Vision Language Models with Early Exits ACL 2025 Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles AAAI 2025 FREE-Merging: Fourier Transform for Efficient Model Merging ICCV 2025 FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers IJCAI 2025 From Attention to Activation: Unraveling the Enigmas of Large Language Models ICLR 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 Fundamental Limitations on Subquadratic Alternatives to Transformers ICLR 2025 FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation EMNLP 2025 GAP: a Global Adaptive Pruning Method for Large Language Models EMNLP 2025 Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher ICLR 2025 Gated Delta Networks: Improving Mamba2 with Delta Rule ICLR 2025 GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning EMNLP 2025 Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations ICCV 2025 GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocation EMNLP 2025 Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization COLING 2025 GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference IJCNLP 2025 Graceful Forgetting in Generative Language Models EMNLP 2025 Gradient Weight-normalized Low-rank Projection for Efficient LLM Training AAAI 2025 GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models ACL 2025 Grammar Pruning: Enabling Low-Latency Zero-Shot Task-Oriented Language Models for Edge AI EMNLP 2025