Model Compression

A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression EMNLP 2024 A Simple and Effective Pruning Approach for Large Language Models ICLR 2024 A Survey on Efficient Federated Learning Methods for Foundation Model Training IJCAI 2024 Asymmetric Masked Distillation for Pre-Training Small Foundation Models CVPR 2024 Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models CVPR 2024 Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models CVPR 2024 Backdoor Attacks via Machine Unlearning AAAI 2024 Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model ACL 2024 BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NeurIPS 2024 BASS: Batched Attention-optimized Speculative Sampling ACL 2024 Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming NeurIPS 2024 Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression EMNLP 2024 BiDM: Pushing the Limit of Quantization for Diffusion Models NeurIPS 2024 Binarized Diffusion Model for Image Super-Resolution NeurIPS 2024 BiPFT: Binary Pre-trained Foundation Transformer with Low-Rank Estimation of Binarization Residual Polynomials AAAI 2024 BitDelta: Your Fine-Tune May Only Be Worth One Bit NeurIPS 2024 BitsFusion: 1.99 bits Weight Quantization of Diffusion Model NeurIPS 2024 BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models NeurIPS 2024 BMRS: Bayesian Model Reduction for Structured Pruning NeurIPS 2024 BMX: Boosting Natural Language Generation Metrics with Explainability EACL 2024 BOLD: Boolean Logic Deep Learning NeurIPS 2024 BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning CVPR 2024 Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers NeurIPS 2024 Building Variable-Sized Models via Learngene Pool AAAI 2024 BVT-IMA: Binary Vision Transformer with Information-Modified Attention AAAI 2024