Model Compression

StitchLLM: Serving LLMs, One Block at a Time ACL 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025 Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation AAAI 2025 Structuring Radiology Reports: Challenging LLMs with Lightweight Models EMNLP 2025 Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training Efficiency EMNLP 2025 STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning ACL 2025 SwiftPrune: Hessian-Free Weight Pruning for Large Language Models EMNLP 2025 SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025 TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning ACL 2025 TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data NAACL 2025 Talking Head Anime 4: Distillation for Real-Time Performance WACV 2025 TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models ACL 2025 Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers AAAI 2025 TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation EMNLP 2025 Temporal Action Detection Model Compression by Progressive Block Drop CVPR 2025 Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models WACV 2025 The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Models EMNLP 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues AAAI 2025 ThinkSLM: Towards Reasoning in Small Language Models EMNLP 2025 ToDi: Token-wise Distillation via Fine-Grained Divergence Control EMNLP 2025 Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025 Token Level Routing Inference System for Edge Devices ACL 2025 TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability EMNLP 2025