Researchers present Secure On-Policy Distillation (SecOPD), a defensive fine-tuning approach that provides token-level feedback to guide training rather than the…
Researchers introduce CyberFactory, an open-source framework that integrates data construction, trajectory synthesis, and model training across three cybersecurity tasks: proof-of-concept…
Princeton University researchers present Recuris, an architecture for long-horizon agent tasks built on two coupled memory systems: a Working Memory…
Researchers introduce OPDVR, a method integrating on-policy distillation with verifiable reward signals for language model training. The approach reformulates on-policy…
Researchers introduce BPCO, a reinforcement learning recipe combining decoupled PPO, bounded value predictions, Monte Carlo targets, and adaptive advantage estimation…
Researchers developed a full-stack framework comprising GameUI-Taxonomy and G2WEngine that automatically extracts reusable UI assets from real gameplay footage and…
A research survey organizes the smart-glasses field around seven interdependent foundational capabilities and proposes an L0-L5 framework spanning capture, reactive…
Researchers propose Meta^n, a system where a fixed meta-operation is recursively applied to its own outputs, with each layer reading…
Researchers introduce a large-scale open video dataset containing 80 million videos totaling 10 million hours of content for multimodal learning…
Tencent Hunyuan researchers introduce CAFE, a framework in which a shared-parameter model alternates between agent and critic roles to build…
Researchers present AgentRoom, a real-time collaborative editing protocol that enables concurrent multi-agent LLM coding through a shared filesystem built on…
Researchers convert agent execution traces into compact finite-state machines containing 7 to 43 states that reconstruct held-out data with 0.997…
