| A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness | May 27, 2024 | ARCDecoder | —Unverified | 0 |
| On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding | May 27, 2024 | Position | —Unverified | 0 |
| Position: Foundation Agents as the Paradigm Shift for Decision Making | May 27, 2024 | Decision MakingPosition | CodeCode Available | 2 |
| Transformers Can Do Arithmetic with the Right Embeddings | May 27, 2024 | GPUPosition | CodeCode Available | 3 |
| GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction | May 27, 2024 | 3D Semantic Occupancy PredictionAutonomous Driving | CodeCode Available | 4 |
| Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups | May 25, 2024 | Position | —Unverified | 0 |
| Base of RoPE Bounds Context Length | May 23, 2024 | Position | —Unverified | 0 |
| LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate | May 22, 2024 | Adversarial AttackAttribute | CodeCode Available | 0 |
| A temporal enhanced semi-supervised segmentation network for needle detection in 3D ultrasound images | May 21, 2024 | Image SegmentationMedical Image Segmentation | —Unverified | 0 |
| Robustly encoding certainty in a metastable neural circuit model | May 21, 2024 | Position | CodeCode Available | 0 |
