Gang Chen

Identical physical AI behaviors often mask fundamentally incompatible developmental origins, yet every major paradigm from generative world models to morphological co-design reduces to just seven core formation sources.

LLM embedding models waste over 40% of their inference compute processing prefix tokens that become completely redundant at deeper layers, enabling aggressive, training-free token pruning with virtually zero retrieval degradation.

Achieving high-quality model performance with just 10% of the required labels could revolutionize the scalability of RLVR in large language models.

A fixed span can recover most of the benefits of movable low-rank factors in LLM adaptation, achieving superior performance with drastically fewer trainable parameters.

Dense retrievers miss the mark on answerability, dropping QA performance drastically despite high semantic relevance, revealing a critical oversight in RAG systems.