← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning ICCV 2025
Task-Specific Zero-shot Quantization-Aware Training for Object Detection ICCV 2025
PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning ICCV 2025
Mobile Video Diffusion ICCV 2025
Importance-Based Token Merging for Efficient Image and Video Generation ICCV 2025
TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025
Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection ICCV 2025
Harnessing Input-Adaptive Inference for Efficient VLN ICCV 2025
DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025
Advancing Weight and Channel Sparsification with Enhanced Saliency WACV 2025
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning EMNLP 2025
IG-Pruning: Input-Guided Block Pruning for Large Language Models EMNLP 2025
Multimodal Promptable Token Merging for Diffusion Models AAAI 2025
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025
Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study EMNLP 2025
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality EMNLP 2025
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization EMNLP 2025
EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models CVPR 2025
Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference AAAI 2025
CodeArena: Evaluating and Aligning CodeLLMs on Human Preference EMNLP 2025
Steering LLM Reasoning Through Bias-Only Adaptation EMNLP 2025
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025
MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models AAAI 2025
OAC: Output-adaptive Calibration for Accurate Post-training Quantization AAAI 2025
Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications ACL 2025