Papers arxiv:2605.27908 ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations Published on May 27 Submitted by Jie Zhu on May 28 Qwen DianJin Authors: Jie Zhu , , , , , , , Abstract ESC-Skills is a skill-centric framework that discovers and self-evolves executable emo… …
… To this end, we propose MrFlow, a training-free multi-resolution acceleration strategy for pretrained flow-matching models built upon a staged low-to-high-resolution pipeline . …
… Its training pipeline combines MuSGD , a hybrid Muon-SGD optimizer adapted from large language model training; Progressive Loss , which shifts supervision toward the inference-time head; and STAL , a label assignment strategy that guarantees positive coverage for small objects. …
… To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. …
… Experiments across three frontier agents show that persona-skill risks persist across agent backbones and distillation protocols, extending from explicit attributes to communication styles and personality traits. …
… We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. …
… This strategy allows L2P to seamlessly migrate massive latent priors to the pixel space using only 8 GPUs. …
… The geometric guidance is obtained through an occlusion-aware point cloud rendering strategy that resolves visibility ambiguities and provides accurate priors for diffusion-based synthesis. …
… First, a component-decoupled architecture in which robot backends , inference strategies , and transport middlewares form an orthogonal grid: adding a robot or a strategy touches only its own layer. …
Papers arxiv:2606.06473 MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery Published on Jun 4 Submitted by taesiri on Jun 5 Authors: , , , , Shiyang Feng , , , , , , , , , Abstract MLEvolve is an LLM-based multi-agent framework that enables long-horizon machine l… …