Efficient Computing

Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring ACL 2025 Bringing RNNs Back to Efficient Open-Ended Video Understanding ICCV 2025 BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing ICML 2025 Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling ICLR 2025 Building an Elastic Block Storage over EBOFs Using Shadow Views NSDI 2025 Building Massive MIMO Baseband Processing on a Single-Node Supercomputer NSDI 2025 Building Vision Models upon Heat Conduction CVPR 2025 B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens ICCV 2025 Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient ACL 2025 ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development NSDI 2025 Byte Latent Transformer: Patches Scale Better Than Tokens ACL 2025 C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation ACL 2025 C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness AAAI 2025 Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing ICML 2025 Cacheback: Speculative Decoding With Nothing But Cache EMNLP 2025 Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models ICML 2025 Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning EMNLP 2025 Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference EMNLP 2025 CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences ICLR 2025 Calibrated Physics-Informed Uncertainty Quantification ICML 2025 Calibration as a Proxy for Fairness and Efficiency in a Perspectivist Ensemble Approach to Irony Detection EMNLP 2025 CALLIC: Content Adaptive Learning for Lossless Image Compression AAAI 2025 Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence ICML 2025 Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression ICML 2025 Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios? ICML 2025