Techniques

Towards Efficient and Accurate Winograd Convolution via Full Quantization NeurIPS 2023 Towards Fully Quantized Neural Networks For Speech Enhancement Interspeech 2023 Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network NeurIPS 2023 Towards Inadequately Pre-trained Models in Transfer Learning ICCV 2023 Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding ACL 2023 Towards Real-Time Segmentation on the Edge AAAI 2023 Towards Robust Object Detection Invariant to Real-World Domain Shifts ICLR 2023 Towards Stable Backdoor Purification through Feature Shift Tuning NeurIPS 2023 Towards Understanding Omission in Dialogue Summarization ACL 2023 Towards Universal Fake Image Detectors That Generalize Across Generative Models CVPR 2023 Tracking Growth and Decay of Plant Roots in Minirhizotron Images WACV 2023 Trainability Preserving Neural Pruning ICLR 2023 Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NeurIPS 2023 Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis NeurIPS 2023 Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis ICLR 2023 Training Transformers with 4-bit Integers NeurIPS 2023 Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks NeurIPS 2023 Train-Once-for-All Personalization CVPR 2023 TRAMS: Training-free Memory Selection for Long-range Language Modeling EMNLP 2023 Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings NeurIPS 2023 Transformer Meets Boundary Value Inverse Problems ICLR 2023 Transformers for Recognition in Overhead Imagery: A Reality Check WACV 2023 Transforming Visual Scene Graphs to Image Captions ACL 2023 Transition-constant Normalization for Image Enhancement NeurIPS 2023 Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach ICCV 2023