Model Compression

SineLoRA∆: Sine-Activated Delta Compression AAAI 2026 SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping AAAI 2026 Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs AAAI 2026 SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning AAAI 2026 SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs EACL 2026 Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction AAAI 2026 SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization AAAI 2026 SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization AAAI 2026 STEP-Nav: Spatial-Temporal Efficient Visual Token Pruning for Vision-and-Language Navigation with Large Language Models AAAI 2026 Stratified Knowledge-Density Super-Network for Scalable Vision Transformers AAAI 2026 StreamingTOM: Streaming Token Compression for Efficient Video Understanding CVPR 2026 Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging AAAI 2026 TAGQuant: Token-Aware Clustering for Group-Wise Quantization EACL 2026 Task-aware Block Pruning with Output Distribution Signals for Large Language Models EACL 2026 Theory-optimal Quantization Based on Flatness ACL 2026 TOP-RL: Task-Optimized Progressive Token Pruning with Reinforcement Learning for Vision Language Models AAAI 2026 Towards Training-Free and Accurate ANN-to-SNN Conversion via Activation-Aware Redistribution AAAI 2026 Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformers AAAI 2026 Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026 Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization AAAI 2026 Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices AAAI 2026 Two Heads Are Better than One: Distilling Large Language Model Features into Small Models with Feature Decomposition and Mixture AAAI 2026 Two-Stage Regularization-Based Structured Pruning for LLMs ACL 2026