Model Compression

GlitchCleaner: Lightweight Glitch Tokens Repairing by Lossless Gated LoRA in Large Language Models AAAI 2026 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models AAAI 2026 GLOBA: Rethinking Parameter Conflicts in Model Merging AAAI 2026 GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models ACL 2026 Grow-on-Demand: Sparse and Adaptive Expert Expansion for Continual Instruction Tuning AAAI 2026 H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs EACL 2026 Hala Technical Report Building Arabic-Centric Instruction & Translation Models at Scale EACL 2026 HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM Acceleration AAAI 2026 HardF-SNN: Hardware-Friendly Quantization for Spiking Neural Networks with Efficient Integer-Arithmetic-Only Inference AAAI 2026 HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models AAAI 2026 HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract) AAAI 2026 HitKV: Activation Frequency Knows Which Tokens Are Important AAAI 2026 IdiomRanker-X at MWE-2026 AdMIRe 2: Multilingual Idiom-Image Alignment via Low-Rank Adaptation of Cross-Encoders EACL 2026 IMPACT: Importance-Aware Activation Space Reconstruction ACL 2026 Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping AAAI 2026 Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging EACL 2026 InfoQ: Mixed-Precision Quantization via Global Information Flow AAAI 2026 iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification AAAI 2026 Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration EACL 2026 KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral EACL 2026 KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference AAAI 2026 KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache AAAI 2026 KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference EACL 2026 L2-LoRA: Improving Low-Rank Adaptation with Layer-Specific Regularization AAAI 2026 LaCo: Layer-wise Compensation for Pruned Large Language Models ACL 2026