| Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking | Mar 1, 2025 | CPUGPU | CodeCode Available | 1 |
| Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction | Mar 1, 2025 | GPUPose Estimation | —Unverified | 0 |
| Streaming Video Question-Answering with In-context Video KV-Cache Retrieval | Mar 1, 2025 | GPUQuestion Answering | CodeCode Available | 2 |
| Timing-Driven Global Placement by Efficient Critical Path Extraction | Feb 28, 2025 | GPU | —Unverified | 0 |
| TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval | Feb 28, 2025 | CPUGPU | —Unverified | 0 |
| Efficient Jailbreaking of Large Models by Freeze Training: Lower Layers Exhibit Greater Sensitivity to Harmful Content | Feb 28, 2025 | GPUSensitivity | —Unverified | 0 |
| Supporting the development of Machine Learning for fundamental science in a federated Cloud with the AI_INFN platform | Feb 28, 2025 | Distributed ComputingDiversity | —Unverified | 0 |
| AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks | Feb 28, 2025 | CPUGPU | —Unverified | 0 |
| Oscillation-Reduced MXFP4 Training for Vision Transformers | Feb 28, 2025 | GPUQuantization | CodeCode Available | 1 |
| S4ConvD: Adaptive Scaling and Frequency Adjustment for Energy-Efficient Sensor Networks in Smart Buildings | Feb 28, 2025 | GPUState Space Models | CodeCode Available | 0 |
| AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs | Feb 27, 2025 | CPUGPU | —Unverified | 0 |
| SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models | Feb 27, 2025 | GPUKnowledge Distillation | —Unverified | 0 |
| LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis | Feb 27, 2025 | CPUGPU | —Unverified | 0 |
| Scalable Signature Kernel Computations for Long Time Series via Local Neumann Series Expansions | Feb 27, 2025 | GPUTime Series | CodeCode Available | 1 |
| FPGA-Accelerated SpeckleNN with SNL for Real-time X-ray Single-Particle Imaging | Feb 27, 2025 | GPU | —Unverified | 0 |
| Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement | Feb 27, 2025 | Computational EfficiencyCPU | CodeCode Available | 0 |
| Accurate and Scalable Graph Neural Networks via Message Invariance | Feb 27, 2025 | GPUTransductive Learning | CodeCode Available | 0 |
| WaveGAS: Waveform Relaxation for Scaling Graph Neural Networks | Feb 27, 2025 | GPUgraph partitioning | —Unverified | 0 |
| QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects | Feb 27, 2025 | 3D Pose EstimationAction Recognition | —Unverified | 0 |
| Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts | Feb 27, 2025 | Computational EfficiencyGPU | CodeCode Available | 5 |
| Mechanistic PDE Networks for Discovery of Governing Equations | Feb 25, 2025 | GPU | —Unverified | 0 |
| Accelerated Training on Low-Power Edge Devices | Feb 25, 2025 | GPU | —Unverified | 0 |
| Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network | Feb 25, 2025 | DescriptiveDiagnostic | —Unverified | 0 |
| The Power of Graph Signal Processing for Chip Placement Acceleration | Feb 24, 2025 | GPU | —Unverified | 0 |
| Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance | Feb 24, 2025 | GPU | —Unverified | 0 |