Open-Source Models & Weights - Weekly Roundup

Evaluations across seven tasks and three Qwen scales show higher mean accuracy than RandOpt on Countdown, GSM8K, and MATH-500 at every scale, and perturbation geometry is highlighted as a key design choice for population-efficient, gradient-free search around pretrained models.

A diagnostic framework that measures point accuracy alongside dispersion retention, the ratio of predicted to human standard deviation, on 10,000 respondent--question pairs from the World Values Survey (WVS) spanning twelve countries and six continents is developed.

An integrated robotics course framework that organizes these activities around a shared robotic artifact, and offers a structured approach for adapting robotics research workflows into interdisciplinary precollege courses.

This work shows that Kimi Delta Attention (KDA) can realize 2D rotations by combining a single delta-rule transformation with a second reflection supplied by its channel-wise gate, and characterize the expressivity of CKDA and prove that every orthogonal diagonal-plus-rank-one matrix is exactly a CKDA transition matrix.

Control experiments on three cybersecurity datasets covering MITRE ATT&CK network traffic, cyber threat intelligence (CTI), and CVE vulnerability analysis show that reasoning topology substantially affects performance, and Graph reasoning achieves the highest overall accuracy.

A fault-class-matched, layout-aware, width-tiered oracle family: a layout/permutation contract checker and a contract-level metamorphic relation (MR-1) for the metadata channel, a global-phase tracker for the phase channel, and a determinism runner for reproducibility.

A large-scale reproducibility study to systematically investigate the impact of semantic ID design on generative recommendation under a unified experimental framework provides a controlled and reproducible understanding of semantic ID design and offers practical insights for future generative recommender systems.