| A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts | Oct 2, 2024 | 4kGPU | —Unverified | 0 |
| TorchSISSO: A PyTorch-Based Implementation of the Sure Independence Screening and Sparsifying Operator for Efficient and Interpretable Model Discovery | Oct 2, 2024 | GPUModel Discovery | CodeCode Available | 1 |
| VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings | Oct 2, 2024 | GPUGraph Attention | —Unverified | 0 |
| FlashMask: Efficient and Rich Mask Extension of FlashAttention | Oct 2, 2024 | Computational EfficiencyGPU | —Unverified | 0 |
| Scalable and Consistent Graph Neural Networks for Distributed Mesh-based Data-driven Modeling | Oct 2, 2024 | GPUGraph Neural Network | —Unverified | 0 |
| Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters | Oct 2, 2024 | GPU | —Unverified | 0 |
| ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving | Oct 2, 2024 | BenchmarkingDocument Summarization | —Unverified | 0 |
| Lotus: learning-based online thermal and latency variation management for two-stage detectors on edge devices | Oct 1, 2024 | CPUDeep Reinforcement Learning | CodeCode Available | 0 |
| ROK Defense M&S in the Age of Hyperscale AI: Concepts, Challenges, and Future Directions | Oct 1, 2024 | Decision MakingGPU | —Unverified | 0 |
| MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards | Oct 1, 2024 | GPUMixture-of-Experts | —Unverified | 0 |
