Model Compression

BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion EMNLP 2025 BDA-UC3M @ BioLaySumm: Efficient Lay Summarization with Small-Scale SoTA LLMs ACL 2025 Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression EMNLP 2025 Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning CVPR 2025 Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing CVPR 2025 Binarized Neural Network for Multi-spectral Image Fusion CVPR 2025 Binary Event-Driven Spiking Transformer IJCAI 2025 Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework EMNLP 2025 BitNet: 1-bit Pre-training for Large Language Models JMLR 2025 Bitnet.cpp: Efficient Edge Inference for Ternary LLMs ACL 2025 BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Interspeech 2025 Block Circulant Adapter for Large Language Models IJCAI 2025 BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers CVPR 2025 BlockPruner: Fine-grained Pruning for Large Language Models ACL 2025 BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices CVPR 2025 Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation ACL 2025 Boost Embodied AI Models with Robust Compression Boundary IJCAI 2025 Boundary-Conscious Pruning: Hard Set-Aware Model Compression for Efficient Speaker Recognition Interspeech 2025 Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient ACL 2025 Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions ICCV 2025 CASP: Compression of Large Multimodal Models Based on Attention Sparsity CVPR 2025 Certifiably Quantisation-Robust training and inference of Neural Networks AISTATS 2025 Channel Merging: Preserving Specialization for Merged Experts AAAI 2025