semantic information
Semantic information refers to the meanings and relationships of words, phrases, or symbols in a context, crucial for improving natural language understanding in AI models.
- AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
- AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
- AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
- Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
- Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
- Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
- Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
- Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
- FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
- GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving
- Hierarchical Shortest-Path Graph Kernel Network
- Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
- PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
- SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction
- STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
- Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
- Unsupervised Federated Graph Learning