Model Compression

ComLoRA: A Competitive Learning Approach for Enhancing LoRA ICLR 2025 Comparative Knowledge Distillation WACV 2025 Composable Interventions for Language Models ICLR 2025 Compressing tree ensembles through Level-wise Optimization and Pruning ICML 2025 Compression-Aware Computing for Scalable and Sustainable AI AAAI 2025 Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting NAACL 2025 ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning EMNLP 2025 Context-aware Dynamic Pruning for Speech Foundation Models ICLR 2025 Context-Driven Dynamic Pruning for Large Speech Foundation Models Interspeech 2025 Continual Gradient Low-Rank Projection Fine-Tuning for LLMs ACL 2025 Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? ACL 2025 Controllable Memorization in LLMs via Weight Pruning EMNLP 2025 CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter ACL 2025 Correcting the Tamazight Portions of FLORES+ and OLDI Seed Datasets EMNLP 2025 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 CoT-Valve: Length-Compressible Chain-of-Thought Tuning ACL 2025 COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection EMNLP 2025 CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025 CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation AAAI 2025 CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation CVPR 2025 Cyber for AI at SemEval-2025 Task 4: Forgotten but Not Lost: The Balancing Act of Selective Unlearning in Large Language Models SemEval 2025 daDPO: Distribution-Aware DPO for Distilling Conversational Abilities ACL 2025 DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration ACL 2025 DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models ICLR 2025 DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025