| APOLLO: SGD-like Memory, AdamW-level Performance | Dec 6, 2024 | GPUQuantization | CodeCode Available | 3 |
| RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation | Jan 9, 2024 | GPUMath | CodeCode Available | 3 |
| Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray | Feb 7, 2025 | 4kGeneral Knowledge | CodeCode Available | 3 |
| KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization | Jan 31, 2024 | GPUQuantization | CodeCode Available | 3 |
| CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation | Oct 12, 2024 | Conditional Image GenerationGPU | CodeCode Available | 3 |
| Cramming: Training a Language Model on a Single GPU in One Day | Dec 28, 2022 | GPULanguage Modeling | CodeCode Available | 3 |
| Allo: A Programming Model for Composable Accelerator Design | Apr 7, 2024 | GPUHigh-Level Synthesis | CodeCode Available | 3 |
| ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation | Jun 22, 2025 | GPUImage Generation | CodeCode Available | 3 |
| Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning | Feb 26, 2024 | GPUMinecraft | CodeCode Available | 3 |
| Consistency Models Made Easy | Jun 20, 2024 | Computational EfficiencyGPU | CodeCode Available | 3 |
