Baidu’s RAG approach to conflicts between model answers and retrieved knowledge
US20260087055A1 distinguishes factual and semantic conflicts and describes different routes to a final answer.
Read articleAnalysis of IP practice, AI technology and international protection, alongside news from IPLEX. Explore the articles in English.
537 articles and updates
103 articles
US20260087055A1 distinguishes factual and semantic conflicts and describes different routes to a final answer.
Read articleAn analysis of US20260236763A1: speculative decoding, marginal benefit and processing cost, with a hypothetical delivery-support example.
Read articleAn analysis of published US application US20260065050A1, using a hypothetical factory inspection workflow to explain heterogeneous processors, model optimisation and evaluation feedback.
Read articleAn accessible explanation of Attention Residuals, Block AttnRes, the limits of the reported results and the implementation details relevant to AI patent drafting.
Read articleYongduck Kim examines FiX’s feature-wise gates, numerical implementation and paged cache, distinguishing reported gains from unresolved limitations.
Read articleYongduck Kim examines Multi-Head Attention Residuals: depth routing, reported training results, implementation costs and the relationship between technical features and effects.
Read articleWriting for AI Times, IPLEX Managing Partner Yongduck Kim examines the training data behind computer-operating AI agents through U.S. Patent No. 12,585,862.
Read articleExplore how IPLEX combines AI and software expertise with a practical understanding of business strategy. The interview discusses education for founders, mentoring and communication with clients.
Read articleThis guide explains the issues to consider and the materials to prepare when seeking patent protection for AI technology.
Read articleAI Times, a Korean AI publication, has published Managing Partner Yongduck Kim's column on artificial intelligence patents.
Read articleWe advise on applications and patent strategy for AI, generative AI and LLMs, machine learning, deep learning and software.
Read articleReward-based reinforcement learning is increasingly used to improve the reasoning capabilities of large language models. PPO-style policy optimization is a common approach. Methods such as GRPO, Dr.GRPO, GSPO and REINFORCE++ modify advantage estimation or normalization while seeking to avoid excessive policy changes in a single update...
Read article