Efficient Computing

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking CVPR 2025 On Probabilistic Truncation in Privacy-preserving Machine Learning AAAI 2025 OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework EMNLP 2025 OSV: One Step is Enough for High-Quality Image to Video Generation CVPR 2025 Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning ACL 2025 Parallel Continuous Chain-of-Thought with Jacobi Iteration EMNLP 2025 PAVE: Patching and Adapting Video Large Language Models CVPR 2025 Perceptual Video Compression with Neural Wrapping CVPR 2025 PIC: Unlocking Long-Form Text Generation Capabilities of Large Language Models via Position ID Compression ACL 2025 PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram CVPR 2025 PipeThreader: Software-Defined Pipelining for Efficient DNN Execution OSDI 2025 Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters AAAI 2025 Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network AAAI 2025 Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025 Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025 POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation EMNLP 2025 Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse Projectors AAAI 2025 Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025 PROMTEC: Fast LLM Inference Decoding using Prompt Multi-Lookup with Template Database and Common Sequences ACL 2025 Pushing the Limits of BFP on Narrow Precision LLM Inference AAAI 2025 QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm ACL 2025 QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models AAAI 2025 Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025