Model Compression

Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations EMNLP 2025 Large Language Models Are Overparameterized Text Encoders NAACL 2025 LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025 Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval CVPR 2025 LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts EMNLP 2025 LESA: Learnable LLM Layer Scaling-Up ACL 2025 Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model CVPR 2025 Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings COLING 2025 LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion ICCV 2025 LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation ICCV 2025 LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation EMNLP 2025 LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs ACL 2025 LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models ICCV 2025 LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering ACL 2025 LLMs on a Budget? Say HOLA EMNLP 2025 LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models CVPR 2025 Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training ACL 2025 LoRACoE: Improving Large Language Model via Composition-based LoRA Expert EMNLP 2025 LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuning EMNLP 2025 LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation COLING 2025 LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement ICCV 2025 LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025 Low-Bit Quantization Favors Undertrained LLMs ACL 2025 Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning CVPR 2025 Low-Rank Interconnected Adaptation across Layers ACL 2025