Efficient Computing

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models ICML 2025 BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute ICML 2025 Beware of Calibration Data for Pruning Large Language Models ICLR 2025 Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning ICML 2025 Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding NAACL 2025 Beyond Fixed-Length Calibration for Post-Training Compression of LLMs EMNLP 2025 Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers WACV 2025 Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix ICLR 2025 Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning ICML 2025 Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation ACL 2025 Beyond Perspective: Neural 360-Degree Video Compression ICCV 2025 Beyond Text Compression: Evaluating Tokenizers Across Scales ACL 2025 Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs ICCV 2025 Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering ICCV 2025 Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models ACL 2025 BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions ICLR 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution ICML 2025 Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing CVPR 2025 BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models ICLR 2025 Binary Event-Driven Spiking Transformer IJCAI 2025 BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models ICML 2025 BitNet: 1-bit Pre-training for Large Language Models JMLR 2025 Bitnet.cpp: Efficient Edge Inference for Ternary LLMs ACL 2025 BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments ICLR 2025