| VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration | Oct 29, 2024 | GPULanguage Modeling | —Unverified | 0 |
| Revisiting Reliability in Large-Scale Machine Learning Research Clusters | Oct 29, 2024 | GPU | —Unverified | 0 |
| ProMoE: Fast MoE-based LLM Serving using Proactive Caching | Oct 29, 2024 | GPUMixture-of-Experts | —Unverified | 0 |
| Data Generation for Hardware-Friendly Post-Training Quantization | Oct 29, 2024 | Data AugmentationGPU | CodeCode Available | 3 |
| Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs | Oct 29, 2024 | GPURecommendation Systems | CodeCode Available | 0 |
| Motion Graph Unleashed: A Novel Approach to Video Prediction | Oct 29, 2024 | GPUOptical Flow Estimation | CodeCode Available | 0 |
| Memory-Efficient Point Cloud Registration via Overlapping Region Sampling | Oct 29, 2024 | GPUPoint Cloud Registration | —Unverified | 0 |
| ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference | Oct 28, 2024 | CPU | CodeCode Available | 3 |
| Accelerated Bayesian parameter estimation and model selection for gravitational waves with normalizing flows | Oct 28, 2024 | CPUGPU | —Unverified | 0 |
| KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation | Oct 28, 2024 | GPUKnowledge Distillation | CodeCode Available | 1 |
