Wen Jiang

HarnessEvolve not only solves the credit assignment problem but also prevents agents from falling into the traps of shortcut learning and catastrophic forgetting, ensuring robust self-evolution.

CBPO redefines credit assignment in RLVR, enabling precise decision sensitivity that boosts performance across diverse benchmarks.

Mixed-state prototypes allow quantum models to learn new classes without expanding circuit complexity, achieving robust performance with fewer qubits.