Model Compression

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems EMNLP 2025 Scaling Down Text Encoders of Text-to-Image Diffusion Models CVPR 2025 Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025 Scheduling Weight Transitions for Quantization-Aware Training ICCV 2025 SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation ACL 2025 SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models CVPR 2025 Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers ICCV 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 SEPS: A Separability Measure for Robust Unlearning in LLMs EMNLP 2025 Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity EMNLP 2025 Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking CVPR 2025 Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement AAAI 2025 Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster EMNLP 2025 Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe COLING 2025 SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression EMNLP 2025 SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device CVPR 2025 SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models WACV 2025 Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs ACL 2025 SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs ICCV 2025 Sparsifying Mamba EMNLP 2025 SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025 Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications ACL 2025 Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs EMNLP 2025 SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025 Staining and Locking Computer Vision Models Without Retraining ICCV 2025