← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting ACL 2025
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization EMNLP 2025
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025
AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity EMNLP 2025
FREE: Fast and Robust Vision Language Models with Early Exits ACL 2025
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance EMNLP 2025
Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information AAAI 2025
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework EMNLP 2025
Demystifying Small Language Models for Edge Deployment ACL 2025
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge EMNLP 2025
Revisiting Pruning vs Quantization for Small Language Models EMNLP 2025
Speculative Decoding for Multi-Sample Inference EMNLP 2025
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models EMNLP 2025
LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation EMNLP 2025
1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models EMNLP 2025
Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations EMNLP 2025
Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs EMNLP 2025
FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation EMNLP 2025
TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidance EMNLP 2025
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression EMNLP 2025
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025
KurTail : Kurtosis-based LLM Quantization EMNLP 2025
FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference EMNLP 2025
Controllable Memorization in LLMs via Weight Pruning EMNLP 2025
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments ACL 2025