AI.info
Xiangyu Yue
Explore Xiangyu Yue on AI.info.
- Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
- Twins: Learn to Predict Unified Representations with Focal Loss
- InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
- Exploring Reasoning Reward Model for Agents
- AdaTooler-V: Adaptive Tool-Use for Images and Videos
- MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
- OneThinker: All-in-one Reasoning Model for Image and Video
- 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
- ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
- VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning