Jin Cui

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models featured image

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models

Organizing robot experiences in a continuous hierarchical memory to support retrieval and generalization in long-horizon tasks.

yanbin-hu
•
"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework featured image

"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework

Combining complementary teachers through student-aware supervision for more effective reasoning distillation.

jin-cui
•
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation featured image

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation

Aligning diverse reasoning perspectives with the student's evolving capabilities to move beyond passive imitation.

jin-cui
•