JD and CAS IIE Publish Three Papers Defining Self-Taught RLVR
让大模型学会「自己教自己」!京东&中科院信工所连发三篇论文定义Self-Taught RLVR
JD and CAS IIE released three Self-Taught RLVR papers covering RLSD, NPO, and CoPD; RLSD reports that 200 training steps on Qwen3-VL-8B-Instruct exceed GRPO at 400 steps across 8 benchmarks.
Why it matters: JD and the Institute of Information Engineering at CAS published three papers on Self-Taught RLVR, a route where the model generates its own training signal during reinforcement learning, skipping human labels and external reward models.