| Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration | Apr 2, 2024 | AllDecoder | CodeCode Available | 2 |
| Accelerating Transformer Pre-training with 2:4 Sparsity | Apr 2, 2024 | GPU | CodeCode Available | 2 |
| IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT | Apr 2, 2024 | GPUparameter-efficient fine-tuning | CodeCode Available | 1 |
| GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA | Apr 1, 2024 | GPUMultiobjective Optimization | CodeCode Available | 3 |
| Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting | Apr 1, 2024 | Domain GeneralizationGPU | CodeCode Available | 0 |
| LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization | Apr 1, 2024 | Action LocalizationGPU | —Unverified | 0 |
| Enhancing Reasoning Capacity of SLM using Cognitive Enhancement | Apr 1, 2024 | GPULanguage Modelling | —Unverified | 0 |
| GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration | Mar 31, 2024 | DeblurringDenoising | —Unverified | 0 |
| Grid Diffusion Models for Text-to-Video Generation | Mar 30, 2024 | GPUImage Generation | —Unverified | 0 |
| DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference | Mar 30, 2024 | GPU | —Unverified | 0 |