| Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image | Jun 6, 2024 | 3D Scene ReconstructionDepth Estimation | CodeCode Available | 3 |
| MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion | May 30, 2024 | DenoisingGPU | CodeCode Available | 3 |
| Transformers Can Do Arithmetic with the Right Embeddings | May 27, 2024 | GPUPosition | CodeCode Available | 3 |
| Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention | May 27, 2024 | GPULanguage Modeling | CodeCode Available | 3 |
| vHeat: Building Vision Models upon Heat Conduction | May 26, 2024 | Computational EfficiencyGPU | CodeCode Available | 3 |
| NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU | May 12, 2024 | CPUDeep Learning | CodeCode Available | 3 |
| vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention | May 7, 2024 | GPUManagement | CodeCode Available | 3 |
| Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services | Apr 25, 2024 | GPU | CodeCode Available | 3 |
| MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts | Apr 22, 2024 | Common Sense ReasoningGPU | CodeCode Available | 3 |
| SnapKV: LLM Knows What You are Looking for Before Generation | Apr 22, 2024 | 16kGPU | CodeCode Available | 3 |
| TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding | Apr 18, 2024 | GPU | CodeCode Available | 3 |
| MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding | Apr 8, 2024 | GPUMultiple-choice | CodeCode Available | 3 |
| Allo: A Programming Model for Composable Accelerator Design | Apr 7, 2024 | GPUHigh-Level Synthesis | CodeCode Available | 3 |
| BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models | Apr 3, 2024 | GPUMath | CodeCode Available | 3 |
| Tensorized NeuroEvolution of Augmenting Topologies for GPU Acceleration | Apr 2, 2024 | Computational EfficiencyGPU | CodeCode Available | 3 |
| GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA | Apr 1, 2024 | GPUMultiobjective Optimization | CodeCode Available | 3 |
| 94% on CIFAR-10 in 3.29 Seconds on a Single GPU | Mar 30, 2024 | GPU | CodeCode Available | 3 |
| The Unreasonable Ineffectiveness of the Deeper Layers | Mar 26, 2024 | GPUQuantization | CodeCode Available | 3 |
| GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting | Mar 13, 2024 | GPUQuantization | CodeCode Available | 3 |
| Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve | Mar 4, 2024 | GPUScheduling | CodeCode Available | 3 |
| Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning | Feb 26, 2024 | GPUMinecraft | CodeCode Available | 3 |
| TorchCP: A Python Library for Conformal Prediction | Feb 20, 2024 | Conformal PredictionDeep Learning | CodeCode Available | 3 |
| BitDelta: Your Fine-Tune May Only Be Worth One Bit | Feb 15, 2024 | GPU | CodeCode Available | 3 |
| Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models | Feb 10, 2024 | CPUGPU | CodeCode Available | 3 |
| BiLLM: Pushing the Limit of Post-Training Quantization for LLMs | Feb 6, 2024 | BinarizationGPU | CodeCode Available | 3 |
