Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks AAAI 2025

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025

Adaptive Draft-Verification for Efficient Large Language Model Decoding AAAI 2025

PAT: Pruning-Aware Tuning for Large Language Models AAAI 2025

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation AAAI 2025

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs AAAI 2025

Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition AAAI 2025

PrivDNFIS: Privacy-preserving and Efficient Deep Neuro-Fuzzy Inference System AAAI 2025

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration AAAI 2025

Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias AAAI 2025

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead AAAI 2025

Learning to Rewind via Iterative Prediction of Past Weights for Practical Unlearning AAAI 2025

Fast and Slow Gradient Approximation for Binary Neural Network Optimization AAAI 2025

Compression-Aware Computing for Scalable and Sustainable AI AAAI 2025

LoRA Unlearns More and Retains More (Student Abstract) AAAI 2025

A Good Teacher Adapts Their Knowledge for Distillation ICCV 2025

Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations ICCV 2025

Task-Specific Zero-shot Quantization-Aware Training for Object Detection ICCV 2025

Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark ICCV 2025

Knowledge Distillation with Refined Logits ICCV 2025

SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025

KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025

TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs ICCV 2025