Model Compression

Data Generation for Hardware-Friendly Post-Training Quantization WACV 2025 DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models EMNLP 2025 DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization OSDI 2025 Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning ICCV 2025 DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge CVPR 2025 DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing ACL 2025 Demystifying Small Language Models for Edge Deployment ACL 2025 DenseLoRA: Dense Low-Rank Adaptation of Large Language Models ACL 2025 DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models CVPR 2025 Difficulty Diversity and Plausibility: Dynamic Data-Free Quantization WACV 2025 Direct Quantized Training of Language Models with Stochastic Rounding ACML 2025 DisComp: A Two-Stage Prompt Optimization Framework Combining Task-Agnostic and Task-Aware Compression NAACL 2025 DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory COLT 2025 Distilling an End-to-End Voice Assistant Without Instruction Training Data ACL 2025 Distilling Rule-based Knowledge into Large Language Models COLING 2025 Distilling the Knowledge in Data Pruning ICML 2025 DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models ACL 2025 DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations CVPR 2025 Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives ICLR 2025 Does Self-Attention Need Separate Weights in Transformers? NAACL 2025 Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025 DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation ACL 2025 Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs EMNLP 2025 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization ACL 2025 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025