Efficient Computing

Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis ACL 2025 Quantization without Tears CVPR 2025 RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning ACL 2025 RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning UAI 2025 Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling EMNLP 2025 REB-former: RWKV-enhanced E-branchformer for Speech Recognition Interspeech 2025 ReBotNet: Fast Real-Time Video Enhancement WACV 2025 RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs ACL 2025 RemDet: Rethinking Efficient Model Design for UAV Object Detection AAAI 2025 RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability AAAI 2025 Retrofitting Large Language Models with Dynamic Tokenization ACL 2025 Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference ACML 2025 Run LoRA Run: Faster and Lighter LoRA Implementations ACL 2025 Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach Interspeech 2025 SalM²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention AAAI 2025 SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025 Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal AAAI 2025 Scale Efficient Training for Large Datasets CVPR 2025 Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing ACL 2025 Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025 Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai ACL 2025 Scaling up the State Size of RNN LLMs for Long-Context Scenarios ACL 2025 SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation ACL 2025 Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors EMNLP 2025 Segment-Based Attention Masking for GPTs ACL 2025