Deep Learning

Di-PS: System-Algorithm Co-Design for Asynchronous and Heterogeneous Cross-cluster LLM Training at Scale NSDI 2026 DiP: Taming Diffusion Models in Pixel Space CVPR 2026 DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment WACV 2026 Directing Uncertainty-Aware Information Flow for Robust Diffusion Prediction AAAI 2026 Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation CVPR 2026 DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching CVPR 2026 DisCo DETR: Distance-aware Multi-view Contrastive Learning for DETR Pre-training AAAI 2026 Disco-GS: Gaussian Splatting in Dynamic Color Lighting CVPR 2026 Discovering Adaptive Task Dependencies for Efficient Multi-Task Representation Compression CVPR 2026 Discovering Lexical Gaps Using Embeddings from Multilingual LLMs CoNLL 2026 Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation CVPR 2026 Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees ACL 2026 Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery WACV 2026 Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning AAAI 2026 Discrete Structure Augmentation for Graph Convolutional Networks AAAI 2026 Discretization Is Not Always Better: Rethinking Deep Quantization for Asymmetric Image Retrieval AAAI 2026 Discriminative Perception via Anchored Description for Reasoning Segmentation CVPR 2026 Discriminative Self-Supervised Pre-Training for Esophagitis Detection in Upper GI Endoscopy Images MIDL 2026 Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization WACV 2026 Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual Recognition AAAI 2026 Disentangled Textual Priors for Diffusion-based Image Super-Resolution CVPR 2026 Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus CVPR 2026 Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement CVPR 2026 Disentangling for Transfer: Boosting Limited Modalities via Information-Theoretic Regularization and Cross-Modal Reconstruction AAAI 2026 Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer ACL 2026