Model Compression

Information-Bottleneck Driven Binary Neural Network for Change Detection ICCV 2025 Information Theoretic Pruning of Coupled Channels in Deep Neural Networks WACV 2025 Instruction-Following Pruning for Large Language Models ICML 2025 Integrating Independent Layer-Wise Rank Selection with Low-Rank SVD Training for Model Compression: A Theory-Driven Approach IJCAI 2025 Interpreting the Effects of Quantization on LLMs IJCNLP 2025 Iterative Layer Pruning for Efficient Translation Inference EMNLP 2025 JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration AAAI 2025 Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment ICLR 2025 KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models ICLR 2025 KHU_LDI at BioLaySumm2025: Fine-tuning and Refinement for Lay Radiology Report Generation ACL 2025 Knockoff Branch: Model Stealing Attack via Adding Neurons in the Pre-Trained Model WACV 2025 Knowledge Distillation Method for Pruned RNN-T Models via Pruning Bounds Sharing and Losses Confusion Interspeech 2025 Knowledge Distillation with Refined Logits ICCV 2025 KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025 KurTail : Kurtosis-based LLM Quantization EMNLP 2025 KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding ACL 2025 LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation EMNLP 2025 Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers CVPR 2025 Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge EMNLP 2025 Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs ICCV 2025 LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models ACL 2025 LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025 LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid ICLR 2025 Learning from Diverse Reasoning Paths with Routing and Collaboration EMNLP 2025 Learning to Rewind via Iterative Prediction of Past Weights for Practical Unlearning AAAI 2025