Yanshu Li

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection

Towards Generalizable Implicit In-Context Learning with Attention Routing

CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation

C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs

When Multimodal Models “Burn Out”: Diagnosing and Healing Modality Fatigue via MAD + MAC

CognitionLight: Continue, Rethink, or Rollback? Signaling for Persona-Aware Reasoning in Intelligent Agents

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

M²IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering