…Driven by its efficient architecture design and inference optimization, the model can perform real-time full-duplex omni-modal interaction on edge devices with less than 12GB RAM cost. View arXiv page…
…This design allows predictive foundation models , which are typically optimized for specialized data and tasks, to participate in higher-level reasoning and decision-making processes within agentic systems. Eywa can serve as…
…Seth Karten , , , , , , , Abstract A self-improving AI system for embodied agents autonomously refines its own prompts, skills, and memory through continuous learning without environment resets, achieving human-level performance in complex video…
…Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed…
…Guided by these insights, we construct UniSDfull , an integrated pipeline that combines complementary components and achieves the strongest overall performance, improving over the base model by +5.4 points and the strongest…
…Existing methods optimize these capabilities in isolation or with separate reward sources, resulting in partial and conflicting evolution. We propose Skill1, a framework that trains a single policy to co-evolve skill…
…Yilun Zhao , , Tingyu Song , , , Abstract Researchers introduce BRIGHT-Pro, an expanded expert-annotated benchmark for reasoning-intensive retrieval, and RTriever-Synth, an aspect-decomposed synthetic corpus, to improve retriever performance through agentic…
…AI-generated summary The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and…
…from temporal blindness in dynamic environments, but a training-free correction method using quadratic optimization improves performance by addressing pace and path dynamics simultaneously. AI-generated summary Vision-Language-Action (VLA) models…
…However, despite their strong performance in static scene perception, these models remain limited in responding to dynamic human instructions, which restricts their use in interactive applications. Existing editing methods typically rely on…