Tag
A paper from Google discusses separating skill-evolution systems into components like raw execution traces and a persistent wiki of knowledge for AI agents, related to self-improvement concepts.
This article reports on the independent research paper 'Attention Projection Mixing with Exogenous Anchors' by 17-year-old high school student Su Tinghao, which was accepted into the ICML main conference, proposing the ExoFormer model to address the over-smoothing issue in Transformers.
A tweet criticizing an ICLR 2026 paper, pointing out that an open-sourced paper achieved excellent results but actually used test set labels to select parameters, questioning the rigor of top conference peer review.
An Arxiv AI paper on polynomial approximation of activation functions ends with the author's wish to marry his high school sweetheart, highlighting a personal touch in Chinese tech academia.
Two recent arXiv papers found that GPT-5.4 and Claude Opus 4.6 employ a metaprogramming strategy when handling unfamiliar programming languages — generating target code with Python and debugging locally — rather than writing the target language code directly. This strategy is key to distinguishing top-tier agents from average ones, and strategy sophistication matters more than model parameter scale.
This paper introduces S-Agent, which uses spatial tool-use to elicit reasoning for spatial intelligence.