| Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving | Oct 13, 2023 | 3D Semantic SegmentationAutonomous Driving | —Unverified | 0 |
| QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models | Oct 13, 2023 | Computational EfficiencyGPU | CodeCode Available | 1 |
| Polynomial Time Cryptanalytic Extraction of Neural Network Models | Oct 12, 2023 | GPU | CodeCode Available | 0 |
| GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models | Oct 12, 2023 | GPUText to 3D | CodeCode Available | 2 |
| 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering | Oct 12, 2023 | Dynamic ReconstructionGPU | CodeCode Available | 4 |
| Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes | Oct 12, 2023 | GPUNovel View Synthesis | CodeCode Available | 2 |
| QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models | Oct 12, 2023 | GPUQuantization | CodeCode Available | 1 |
| No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML | Oct 11, 2023 | GPUInference Attack | CodeCode Available | 1 |
| QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources | Oct 11, 2023 | GPUparameter-efficient fine-tuning | —Unverified | 0 |
| Transformers for Green Semantic Communication: Less Energy, More Semantics | Oct 11, 2023 | BenchmarkingCPU | CodeCode Available | 0 |
