Model Compression

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation ACL 2024 BitsFusion: 1.99 bits Weight Quantization of Diffusion Model NeurIPS 2024 Black-Box Forgetting NeurIPS 2024 Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication AAAI 2024 BMRS: Bayesian Model Reduction for Structured Pruning NeurIPS 2024 Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding Interspeech 2024 Bootstrapping SparseFormers from Vision Foundation Models CVPR 2024 BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning NeurIPS 2024 Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models EMNLP 2024 Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation NeurIPS 2024 BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation Interspeech 2024 BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models ICLR 2024 Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers NeurIPS 2024 CeeBERT: Cross-Domain Inference in Early Exit BERT ACL 2024 Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing NeurIPS 2024 Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy EMNLP 2024 Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models NeurIPS 2024 CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification EMNLP 2024 CodeAgent: Autonomous Communicative Agents for Code Review EMNLP 2024 Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models EMNLP 2024 Compact 3D Gaussian Representation for Radiance Field CVPR 2024 Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other NAACL 2024 Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation ICML 2024 Compressing Large Language Models using Low Rank and Low Precision Decomposition NeurIPS 2024 Compressing LLMs: The Truth is Rarely Pure and Never Simple ICLR 2024