| Linear Attention Sequence Parallelism | Apr 3, 2024 | 2k | CodeCode Available | 2 | 5 |
| GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis | Dec 4, 2023 | 2kDepth Estimation | CodeCode Available | 2 | 5 |
| HHAvatar: Gaussian Head Avatar with Dynamic Hairs | Dec 5, 2023 | 2k | CodeCode Available | 2 | 5 |
| HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models | Dec 21, 2023 | 2kImage Inpainting | CodeCode Available | 2 | 5 |
| MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization | Jul 14, 2025 | 2kImage Generation | CodeCode Available | 2 | 5 |
| Any-resolution Training for High-resolution Image Synthesis | Apr 14, 2022 | 2kImage Generation | CodeCode Available | 2 | 5 |
| FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning | Mar 30, 2025 | 2kGPU | CodeCode Available | 2 | 5 |
| PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training | Sep 19, 2023 | 2kPosition | CodeCode Available | 2 | 5 |
| High-fidelity 3D Human Digitization from Single 2K Resolution Images | Mar 27, 2023 | 2k3D Human Reconstruction | CodeCode Available | 2 | 5 |
| STICKERCONV: Generating Multimodal Empathetic Responses from Scratch | Jan 20, 2024 | 2kEmpathetic Response Generation | CodeCode Available | 2 | 5 |
