Efficient Computing

LaCoOT: Layer Collapse through Optimal Transport ICCV 2025 LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025 Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers CVPR 2025 LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models ACL 2025 LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025 Learning Hierarchical Line Buffer for Image Processing ICCV 2025 LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation ACL 2025 LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts EMNLP 2025 Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing AAAI 2025 Leveraging Multi-Level Features of ATST with Conformer-Based Dual-Branch Network for Sound Event Detection Interspeech 2025 LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios Interspeech 2025 LLMs on a Budget? Say HOLA EMNLP 2025 Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025 LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025 Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding NAACL 2025 MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection ACL 2025 MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba ICLR 2025 MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025 MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025 METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding EMNLP 2025 MIND over Body: Adaptive Thinking using Dynamic Computation ICLR 2025 MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference ACL 2025 Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025 Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025