Efficient Computing

Masked Generative Nested Transformers with Decode Time Scaling ICML 2025 MaskVD: Region Masking for Efficient Video Object Detection WACV 2025 MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models EMNLP 2025 MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection ICLR 2025 Matryoshka Multimodal Models ICLR 2025 Matryoshka Quantization ICML 2025 MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling ICCV 2025 Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization ICML 2025 MBQ: Modality-Balanced Quantization for Large Vision-Language Models CVPR 2025 MCNC: Manifold-Constrained Reparameterization for Neural Compression ICLR 2025 MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 Mechanistic PDE Networks for Discovery of Governing Equations ICML 2025 MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025 MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation ICCV 2025 MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025 MEGAD: A Memory-Efficient Framework for Large-Scale Attributed Graph Anomaly Detection IJCAI 2025 MegaFusion: Extend Diffusion Models towards Higher-Resolution Image Generation without Further Tuning WACV 2025 MELODI: Exploring Memory Compression for Long Contexts ICLR 2025 MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation ICCV 2025 Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices EMNLP 2025 Memory-Efficient Generative Models via Product Quantization ICCV 2025 Memory Efficient Matting with Adaptive Token Routing AAAI 2025 Memory Efficient Transformer Adapter for Dense Predictions ICLR 2025 Memory Layers at Scale ICML 2025 MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs ICML 2025