Efficient Computing

MoDeGPT: Modular Decomposition for Large Language Model Compression ICLR 2025 ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges EMNLP 2025 Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization ACL 2025 Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models ICCV 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization ICML 2025 MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts ICLR 2025 MoEP: Modular Expert Paths for Sample-Efficient Language Modeling EMNLP 2025 MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance ICML 2025 MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition ICML 2025 MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition ICML 2025 MoH: Multi-Head Attention as Mixture-of-Head Attention ICML 2025 MoleculeMiner: Extracting and Linking Molecule Figures with Tabular Metadata IJCAI 2025 MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition ICML 2025 Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning ICML 2025 MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025 Monolingual Adapter Networks for Efficient Cross-Lingual Alignment EMNLP 2025 MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses ICLR 2025 More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025 Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models ICML 2025 MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards ICLR 2025 mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding ACL 2025 MPPQ: Enhancing Post-Training Quantization for LLMs via Mixed Supervision, Proxy Rounding, and Pre-Searching IJCAI 2025 MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models AAAI 2025 MrT5: Dynamic Token Merging for Efficient Byte-level Language Models ICLR 2025