Techniques

On the Faithfulness of Vision Transformer Explanations CVPR 2024 On the Generalization Ability of Unsupervised Pretraining AISTATS 2024 On the Limitations of Temperature Scaling for Distributions with Overlaps ICLR 2024 On the Over-Memorization During Natural, Robust and Catastrophic Overfitting ICLR 2024 On the Scalability of Diffusion-based Text-to-Image Generation CVPR 2024 On the Scalability of GNNs for Molecular Graphs NeurIPS 2024 On the Semantic Latent Space of Diffusion-Based Text-To-Speech Models ACL 2024 On the Use of Anchoring for Training Vision Models NeurIPS 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Optimizing Diffusion Noise Can Serve As Universal Motion Priors CVPR 2024 Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs EMNLP 2024 Order-Based Pre-training Strategies for Procedural Text Understanding NAACL 2024 Orthogonal Adaptation for Modular Customization of Diffusion Models CVPR 2024 OSIC: A New One-Stage Image Captioner Coined IJCAI 2024 OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport ICML 2024 PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images ICLR 2024 PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video CVPR 2024 Parallel Backpropagation for Shared-Feature Visualization NeurIPS 2024 Parameter-efficient Fine-tuning of Speaker-Aware Dynamic Prompts for Speaker Verification Interspeech 2024 Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model CVPR 2024 Parameter-Efficient Multi-Task Model Fusion with Partial Linearization ICLR 2024 Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation ICML 2024 Parameter-Inverted Image Pyramid Networks NeurIPS 2024 Parameterized Projected Bellman Operator AAAI 2024 ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks CVPR 2024