Model Compression

Calibrating Beyond English: Language Diversity for Better Quantized Multilingual LLMs EACL 2026 CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis AAAI 2026 CanKD: Cross-Attention-based Non-local Operation for Feature-based Knowledge Distillation WACV 2026 Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression ACL 2026 CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model CVPR 2026 C-GNN-PRUNE: A Unified Graph-Based Framework for Structure-Aware Pruning of Mixture-of-Experts Models AAAI 2026 CLoCKDistill: Consistent Location and Context aware Knowledge Distillation for DETRs WACV 2026 CMedBench: A Comprehensive Benchmark for Efficient Medical Large Language Models AAAI 2026 CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices AAAI 2026 Collaborative Multi-Mode Pruning for Vision-Language Models CVPR 2026 CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints AAAI 2026 Compact Language Models with Iterative Text Refinement for Health Dialogue Summarization EACL 2026 Compressing Language Models for Specialized Domains EACL 2026 CP-Router: An Uncertainty-Aware Router Between LLM and LRM AAAI 2026 D2MoRA: Diversity-Regulated Asymmetric MoE-LoRA Decomposition for Efficient Multi-Task Adaptation AAAI 2026 D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning AAAI 2026 D2 Prune: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness AAAI 2026 DeepTracer: Tracing Stolen Model via Deep Coupled Watermarks AAAI 2026 Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models WACV 2026 Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability AAAI 2026 DesireKV: Decoupling Sensitivity and Importance for Reasoning-Aware KV Cache Compression AAAI 2026 Direction Sensitivity–Based Knowledge Distillation: Optimization-Aware Low-Rank Knowledge Transfer AAAI 2026 Discretization Is Not Always Better: Rethinking Deep Quantization for Asymmetric Image Retrieval AAAI 2026 Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory AAAI 2026 Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT AAAI 2026