开源的角色模型路由器，用能力感知协议打通本地与云端AI调度，让请求精准匹配端点。
Hey everyone, I'm launching role-model today: a routing protocol, a reference router runtime, and an extension for Pi that allows for better informed …
视频大模型推理长度不再是死板固定，CARE用能力感知奖励塑形实现自适应思考，效率与精度兼顾。
arXiv:2606.19927v1 Announce Type: new Abstract: In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and i…
重力感知分层路由让传感器上的轻量级LLM更高效地识别人类活动
arXiv:2606.04019v1 Announce Type: cross Abstract: Recent studies on sensor-language alignment have shown that two-stage frameworks can improve the sem…
提出CARE-RL框架，通过能力感知机制缓解强化学习中的跨域冲突，实现多任务协同优化。
arXiv:2606.00609v1 Announce Type: new Abstract: Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented…
提出力感知神经切线核方法，攻克机器学习力场主动学习在大规模候选池及偏差下的扩展性与鲁棒性难题
arXiv:2605.13788v2 Announce Type: replace Abstract: Active learning for machine-learning interatomic potentials (MLIPs) must address several challenge…