Model Compression

Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps ACL 2025 Revisiting Pruning vs Quantization for Small Language Models EMNLP 2025 RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model Accuracy AAAI 2025 RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals EMNLP 2025 Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels ICCV 2025 RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates ACL 2025 RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations IJCAI 2025 Run LoRA Run: Faster and Lighter LoRA Implementations ACL 2025 RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization ICML 2025 SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025 SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation WACV 2025 Sample-aware Adaptive Structured Pruning for Large Language Models AAAI 2025 SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens CVPR 2025 Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems EMNLP 2025 Scaling Down Text Encoders of Text-to-Image Diffusion Models CVPR 2025 Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025 Security Attacks on LLM-based Code Completion Tools AAAI 2025 Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation CVPR 2025 Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models EMNLP 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity EMNLP 2025 ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers ICCV 2025 Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement AAAI 2025 Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping ICCV 2025 SLADE: Shielding against Dual Exploits in Large Vision-Language Models CVPR 2025