Efficient Computing

Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws ICLR 2025 Picsou: Enabling Replicated State Machines to Communicate Efficiently OSDI 2025 PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization ICML 2025 PipeThreader: Software-Defined Pipelining for Efficient DNN Execution OSDI 2025 PISCO: Pretty Simple Compression for Retrieval-Augmented Generation ACL 2025 Pisets: A Robust Speech Recognition System for Lectures and Interviews NAACL 2025 Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models ICML 2025 Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach CVPR 2025 PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts NAACL 2025 PLEX: Adaptive Parameter-Efficient Fine-Tuning for Code LLMs using Lottery-Tickets NAACL 2025 Plug-and-Play Versatile Compressed Video Enhancement CVPR 2025 Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models ACL 2025 p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay ICCV 2025 PNVC: Towards Practical INR-based Video Compression AAAI 2025 PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning CVPR 2025 PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning AAAI 2025 POLO: An LLM-Powered Project-Level Code Performance Optimization Framework IJCAI 2025 Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters AAAI 2025 Portcullis: A Scalable and Verifiable Privacy Gateway for Third-Party LLM Inference AAAI 2025 Position: AI Scaling: From Up to Down and Out ICML 2025 Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025 Position: Enough of Scaling LLMs! Lets Focus on Downscaling ICML 2025 Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models EMNLP 2025 Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives ICML 2025 Powerformer: Efficient and High-Accuracy Privacy-Preserving Language Model with Homomorphic Encryption ACL 2025