Efficient Computing

MKD: Multi-Knowledge Distillation for Real-Time Object Detection on Edge Devices ACML 2025 MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices CVPR 2025 MobiLoRA: Accelerating LoRA-based LLM Inference on Mobile Devices via Context-aware KV Cache Optimization ACL 2025 MSFNet: A Nested Model for Multi-Sampling-Frequency Speech Enhancement Interspeech 2025 Multi-HexPlanes: A Lightweight Map Representation for Rendering and 3D Reconstruction WACV 2025 Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention ACL 2025 NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning EMNLP 2025 Neuromorphic Sequential Arena: A Benchmark for Neuromorphic Temporal Processing IJCAI 2025 NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding Interspeech 2025 Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners Interspeech 2025 OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework ICLR 2025 On-device Streaming Discrete Speech Units Interspeech 2025 Online AV-CrossNet: a Causal and Efficient Audiovisual System for Speech Enhancement and Target Speaker Extraction Interspeech 2025 Optimizing Trajectory Matching Distillation via Parameter Difference-Driven Pruning ACML 2025 PEARL: Parallel Speculative Decoding with Adaptive Draft Length ICLR 2025 Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios NAACL 2025 PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts NAACL 2025 Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025 Position Really Matters: Towards a Holistic Approach for Prompt Tuning NAACL 2025 Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models AISTATS 2025 Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models ICCV 2025 Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers CVPR 2025 QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm ACL 2025