Model Compression

Language Model Distillation: A Temporal Difference Imitation Learning Perspective AAAI 2026 LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models AAAI 2026 LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention AAAI 2026 LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation ACL 2026 Learnable Permutation for Structured Sparsity on Transformer Models AAAI 2026 Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026 LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators AAAI 2026 LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit AAAI 2026 LLM-Oriented Token-Adaptive Knowledge Distillation AAAI 2026 LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers AAAI 2026 Logits-Based Block Pruning with Affine Transformations for Large Language Models EACL 2026 LoKI: Low-Damage Knowledge Implanting of Large Language Models AAAI 2026 LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping AAAI 2026 LS-ViT: Least-Squares Hessian Based Block Reconstruction for Low-Bit Post-Training Quantization of Vision Transformers CVPR 2026 Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off AAAI 2026 Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code EACL 2026 MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models CVPR 2026 MCW-KD: Multi-Cost Wasserstein Knowledge Distillation for Large Language Models AAAI 2026 MemeBQ:Memory Efficient Binary Quantization of LLMs AAAI 2026 MHA2MLA-VLM: Enabling DeepSeek’s Economical Multi-Head Latent Attention Across Vision-Language Models AAAI 2026 Mitigating Copy Bias in In-Context Learning through Neuron Pruning EACL 2026 MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection Under Cloaking Perturbations AAAI 2026 MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs AAAI 2026 MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation AAAI 2026 Mosaic Pruning: A Hierarchical Framework for Generalizable Pruning of Mixture-of-Experts Models AAAI 2026