Model Compression

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition ACL 2025 A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025 AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations COLING 2025 ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models CVPR 2025 A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention ICLR 2025 AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution ICLR 2025 Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression CVPR 2025 Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety EMNLP 2025 Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression ICLR 2025 BeamLoRA: Beam-Constraint Low-Rank Adaptation ACL 2025 Beware of Calibration Data for Pruning Large Language Models ICLR 2025 Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression EMNLP 2025 Beyond Fixed-Length Calibration for Post-Training Compression of LLMs EMNLP 2025 Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs AAAI 2025 Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix ICLR 2025 Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation EMNLP 2025 BHViT: Binarized Hybrid Vision Transformer CVPR 2025 Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach COLING 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing CVPR 2025 Binarized Neural Network for Multi-spectral Image Fusion CVPR 2025 BinarySelect to Improve Accessibility of Black-Box Attack Research COLING 2025 Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework EMNLP 2025 BitMar: Low-Bit Multimodal Fusion with Episodic Memory for Edge Devices EMNLP 2025 BitNet: 1-bit Pre-training for Large Language Models JMLR 2025