real-world scenarios
Real-world scenarios in AI refer to the practical applications and challenges that AI systems face when deployed in everyday situations. This term emphasizes the importance of ensuring that models can generalize well beyond controlled test conditions to effectively operate in complex and dynamic environments.
- Can Class-Priors Help Single-Positive Multi-Label Learning?
- Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models
- Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
- Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks
- Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline
- FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
- LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
- MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
- Normal-Abnormal Guided Generalist Anomaly Detection
- OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations
- PASS: Path-selective State Space Model for Event-based Recognition
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- Seeing the Wind from a Falling Leaf
- Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
- VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
- VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation