Efficient Computing

Assessing the Performance and Efficiency of Mamba ASR in Low-Resource Scenarios Interspeech 2025 A Stochastic Approach to the Subset Selection Problem via Mirror Descent ICLR 2025 Attention-Free Dual-Mode ASR with Latency-Controlled Selective State Spaces Interspeech 2025 Automated Fine-Grained Mixture-of-Experts Quantization ACL 2025 B2Opt: Learning to Optimize Black-box Optimization with Little Budget AAAI 2025 Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models EMNLP 2025 Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation AAAI 2025 Benchmarking Predictive Coding Networks -- Made Simple ICLR 2025 Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025 Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS ICCV 2025 Binary Event-Driven Spiking Transformer IJCAI 2025 Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework EMNLP 2025 BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Interspeech 2025 BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host Caching OSDI 2025 Boundary-Conscious Pruning: Hard Set-Aware Model Compression for Efficient Speaker Recognition Interspeech 2025 Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection CVPR 2025 Breaking Resource Barriers in Speech Emotion Recognition via Data Distillation Interspeech 2025 Building Vision Models upon Heat Conduction CVPR 2025 CAGCRN: Real-Time Speech Enhancement with a Lightweight Model for Joint Acoustic Echo Cancellation and Noise Suppression Interspeech 2025 Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices CVPR 2025 CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction CVPR 2025 CAX: Cellular Automata Accelerated in JAX ICLR 2025 CBQ: Cross-Block Quantization for Large Language Models ICLR 2025 CipherPrune: Efficient and Scalable Private Transformer Inference ICLR 2025 CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025