conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1,952 papers

Papers per year

6
114
489
'15
'20
'25

Papers

Beyond Fixed-Length Calibration for Post-Training Compression of LLMs EMNLP 2025
NormAL LoRA: What is the perfect size? EMNLP 2025
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs EMNLP 2025
Riemannian Optimization for LoRA on the Stiefel Manifold EMNLP 2025
Mamba Drafters for Speculative Decoding EMNLP 2025
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging EMNLP 2025
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction EMNLP 2025
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation EMNLP 2025
SpecCoT: Accelerating Chain-of-Thought Reasoning through Speculative Exploration EMNLP 2025
GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning EMNLP 2025
Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models EMNLP 2025
BitMar: Low-Bit Multimodal Fusion with Episodic Memory for Edge Devices EMNLP 2025
Zero-Shot Cross-Lingual Transfer using Prefix-Based Adaptation EMNLP 2025
Hypernetworks for Perspectivist Adaptation EMNLP 2025
Efficient On-Device Text Simplification for Firefox with Synthetic Data Fine-Tuning EMNLP 2025
OneNRC@TSAR2025 Shared Task Small Models for Readability Controlled Text Simplification EMNLP 2025
Findings of the WMT 2025 Shared Task on Model Compression: Early Insights on Compressing LLMs for Machine Translation EMNLP 2025
Submission for WMT25 Task 3 EMNLP 2025
Vicomtech@WMT 2025: Evolutionary Model Compression for Machine Translation EMNLP 2025
Iterative Layer Pruning for Efficient Translation Inference EMNLP 2025
Correcting the Tamazight Portions of FLORES+ and OLDI Seed Datasets EMNLP 2025
Information-Bottleneck Driven Binary Neural Network for Change Detection ICCV 2025
Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts ICCV 2025
FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models ICCV 2025