| STAT: Shrinking Transformers After Training | May 29, 2024 | DecoderGPU | —Unverified | 0 |
| MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models | May 29, 2024 | DecoderGPU | —Unverified | 0 |
| Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification | May 29, 2024 | Contrastive LearningDenoising | —Unverified | 0 |
| Spatio-Spectral Graph Neural Networks | May 29, 2024 | GPUGraph Classification | CodeCode Available | 1 |
| Cardiovascular Disease Detection from Multi-View Chest X-rays with BI-Mamba | May 28, 2024 | Computed Tomography (CT)GPU | CodeCode Available | 1 |
| Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference | May 28, 2024 | GPUText Generation | CodeCode Available | 2 |
| Pipette: Automatic Fine-grained Large Language Model Training Configurator for Real-World Clusters | May 28, 2024 | GPULanguage Modeling | CodeCode Available | 0 |
| DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention | May 28, 2024 | GPUMamba | CodeCode Available | 2 |
| Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations | May 28, 2024 | GPU | CodeCode Available | 2 |
| Cycle-YOLO: A Efficient and Robust Framework for Pavement Damage Detection | May 28, 2024 | GPU | —Unverified | 0 |
| Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model | May 28, 2024 | GPUMamba | —Unverified | 0 |
| ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention | May 28, 2024 | GPURepresentation Learning | CodeCode Available | 2 |
| Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention | May 27, 2024 | GPULanguage Modeling | CodeCode Available | 3 |
| CudaSIFT-SLAM: multiple-map visual SLAM for full procedure mapping in real human endoscopy | May 27, 2024 | GPUSimultaneous Localization and Mapping | —Unverified | 0 |
| Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training | May 27, 2024 | DecoderGPU | —Unverified | 0 |
| TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models | May 27, 2024 | Backdoor AttackGPU | CodeCode Available | 0 |
| SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs | May 27, 2024 | GPU | —Unverified | 0 |
| Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings | May 27, 2024 | Domain AdaptationGPU | —Unverified | 0 |
| Transformers Can Do Arithmetic with the Right Embeddings | May 27, 2024 | GPUPosition | CodeCode Available | 3 |
| LoQT: Low-Rank Adapters for Quantized Pretraining | May 26, 2024 | GPULanguage Modeling | CodeCode Available | 2 |
| GPU Based Differential Evolution: New Insights and Comparative Study | May 26, 2024 | GPU | —Unverified | 0 |
| vHeat: Building Vision Models upon Heat Conduction | May 26, 2024 | Computational EfficiencyGPU | CodeCode Available | 3 |
| The devil is in discretization discrepancy. Robustifying Differentiable NAS with Single-Stage Searching Protocol | May 26, 2024 | GPUNeural Architecture Search | —Unverified | 0 |
| Apply Distributed CNN on Genomics to accelerate Transcription-Factor TAL1 Motif Prediction | May 25, 2024 | Deep LearningGPU | —Unverified | 0 |
| MINet: Multi-scale Interactive Network for Real-time Salient Object Detection of Strip Steel Surface Defects | May 25, 2024 | CPUDefect Detection | CodeCode Available | 1 |
