AI.info

Yi Yang

Explore Yi Yang on AI.info.

• Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
• RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
• Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
• Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
• Kimi K2.5: Visual Agentic Intelligence
• V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation
• EvasionBench: A Large-Scale Benchmark for Detecting Managerial Evasion in Earnings Call Q&A
• CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
• 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
• Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
• Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
• GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
• Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling