Model Compression

Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models CVPR 2026 MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning AAAI 2026 MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models WACV 2026 MultiKD: Backdoor Defense in Federated Graph Learning via Attention-Guided Multi-Teacher Distillation AAAI 2026 Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships WACV 2026 Navigating Data Scarcity in Low-Resource English-Tatar Translation using LLM Fine-Tuning EACL 2026 Neural-Augmented Kelvinlet for Real-Time Soft Tissue Deformation Modeling AAAI 2026 Neural Differentiation in Deep Networks: A Theoretical Framework for Expressivity and Representational Diversity CVPR 2026 Not All Tokens Are Meant to Be Forgotten AAAI 2026 OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions EACL 2026 One-Cycle Structured Pruning via Stability-Driven Subnetwork Search WACV 2026 On the Impact of Weight Quantization on Deep Neural Network Uncertainty AAAI 2026 Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging AAAI 2026 PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference EACL 2026 Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules EACL 2026 Paths Not Taken: Structure-Based Pruning in PSDD Learning and Inference AAAI 2026 PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark EACL 2026 Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget EACL 2026 POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs EACL 2026 PocketLLM: Ultimate Compression of Large Language Models via Meta Networks AAAI 2026 PosPrune: Visual Token Pruning with Positional Bias Correction for Efficient Large Vision-Language Models AAAI 2026 Progressive Multi-modal Knowledge Distillation for Multi-spectral Object Re-identification AAAI 2026 Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs ACL 2026 Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks AAAI 2026 PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language Models AAAI 2026