Efficient Computing

SMamba: Sparse Mamba for Event-based Object Detection AAAI 2025 Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025 SMART: Self-Aware Agent for Tool Overuse Mitigation ACL 2025 SparseAlign: a Fully Sparse Framework for Cooperative Object Detection CVPR 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds Interspeech 2025 Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025 SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025 SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility ICCV 2025 Spiking Transformer with Spatial-Temporal Attention CVPR 2025 SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition ICCV 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech Enhancement Interspeech 2025 STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation IJCAI 2025 Stochastic Rounding for LLM Training: Theory and Practice AISTATS 2025 Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More EMNLP 2025 Structured Codebook Based Hierarchical Framework for DNN for Computationally Efficient Speech Enhancement Interspeech 2025 STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning ACL 2025 Surprising Effectiveness of pretraining Ternary Language Model at Scale ICLR 2025 Synonymity-Based Semantic Coding for Efficient Speech Compression Interspeech 2025 Tackling Long-Tailed Data Challenges in Spiking Neural Networks via Heterogeneous Knowledge Distillation IJCAI 2025 TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice ICLR 2025 Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks CVPR 2025 TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025