model compression

Does Self-Attention Need Separate Weights in Transformers? NAACL 2025 Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025 DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle ICLR 2025 DP-FROST: Differentially Private Fine-tuning of Pre-trained Models with Freezing Model Parameters COLING 2025 DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models AAAI 2025 DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers ACL 2025 DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching CVPR 2025 Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs EMNLP 2025 DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models ICLR 2025 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 DTDES-KGE: Dual-Teacher Knowledge Distillation with Distinct Embedding Spaces for Knowledge Graph Embeddings EMNLP 2025 DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads ICLR 2025 DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs EMNLP 2025 Dynamic Operator Optimization for Efficient Multi-Tenant LoRA Model Serving AAAI 2025 Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM ICCV 2025 DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception WACV 2025 EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models ACL 2025 EA-KD: Entropy-based Adaptive Knowledge Distillation ICCV 2025 EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models EMNLP 2025 EA-Vit: Efficient Adaptation for Elastic Vision Transformer ICCV 2025 ECCC: Edge Code Cloak Coder for Privacy Code Agent EMNLP 2025 ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025 EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models EMNLP 2025 EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices ACL 2025 Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning CVPR 2025