| Scaling Down Text Encoders of Text-to-Image Diffusion Models | Mar 25, 2025 | GPUImage Generation | CodeCode Available | 2 |
| BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache | Mar 24, 2025 | Computational EfficiencyGPU | CodeCode Available | 2 |
| Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping | Mar 21, 2025 | GPUMotion Estimation | CodeCode Available | 2 |
| DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding | Mar 20, 2025 | GPU | CodeCode Available | 2 |
| Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels | Mar 18, 2025 | GPULanguage Modeling | CodeCode Available | 2 |
| MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling | Mar 17, 2025 | GPULanguage Modeling | CodeCode Available | 2 |
| RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds | Mar 16, 2025 | GPU | CodeCode Available | 2 |
| LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization | Mar 11, 2025 | GPUImage Generation | CodeCode Available | 2 |
| OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models | Mar 11, 2025 | GPUMamba | CodeCode Available | 2 |
| X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation | Mar 8, 2025 | GPUImage Generation | CodeCode Available | 2 |
