Model Compression

Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study AAAI 2025 SpecCoT: Accelerating Chain-of-Thought Reasoning through Speculative Exploration EMNLP 2025 Speculative Decoding for Multi-Sample Inference EMNLP 2025 SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking ICLR 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 SpinQuant: LLM Quantization with Learned Rotations ICLR 2025 SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025 Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs EMNLP 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation NAACL 2025 SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025 Streamlining Redundant Layers to Compress Large Language Models ICLR 2025 Stronger Universal and Transferable Attacks by Suppressing Refusals NAACL 2025 STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning ACL 2025 Submission for WMT25 Task 3 EMNLP 2025 SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning ACL 2025 SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression ICLR 2025 SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression NAACL 2025 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering AAAI 2025 SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration ICLR 2025 SwiftPrune: Hessian-Free Weight Pruning for Large Language Models EMNLP 2025 SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning ICLR 2025 Systematic Outliers in Large Language Models ICLR 2025 TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models ACL 2025 TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning ACL 2025