Weekly Reads

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design — Hongyang Du, Lan Yan et al.
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet out...
MintAct: A Unified Visual Agent for Digital Environments — Mingfei Gao, Rui Tian et al.
We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual...
Cross-sector generalization of accident-process role classification in occupational accident narratives — Aho Yapi, Pierre Latouche et al.
Occupational accident narratives contain valuable information about work situations, unfavourable conditions, accident events, and their consequenc...
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation — Wenxue Li, Peiyan Guan et al.
Reference-to-video (R2V) generation is evolving toward increasingly general and versatile reference control, giving rise to the emerging paradigm o...
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself — Bowen Ye, Lei Li et al.
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich s...

Introducing the Australian Youth Safety Blueprint — OpenAI Blog
OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.
How Cooley is accelerating IPO work with ChatGPT — OpenAI Blog
Cooley built GO Public with ChatGPT Work to bring intelligence to the IPO process, helping lawyers surface issues earlier and focus judgment where ...
Introducing Astra for Law — OpenAI Blog
OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential...