Mechanistic interpretability (MI) aims to explain a model's behaviour through analyzing its internal computations; circuit-based explanations aim to isolate these computations with compact subnetworks validated by ablating the rest of the model. We show that circuits validated this way may fail to recover the underlyin...
Li Zhang, Chu-Qin Geng, Mark Zhang et al.· 0 citations
OmniRouting is the first large-scale benchmark designed to evaluate LLMs on printed-circuit-board (PCB) routing reasoning under real-world industrial design-rule, manufacturability, and connectivity constraints, and reveals substantial limitations of current LMMs in PCB routing.
Tai-Ting Lu, Kai-Yuan Lin, Zi-Wei Dong et al.· 0 citations
OmniLayout, the first benchmark designed to evaluate LLMs on printed-circuit-board (PCB) layout placement reasoning under real-world geometric, routing, and connectivity constraints, reveals substantial limitations of current LLMs in PCB layout placement, including weak geometric reasoning, poor routability optimizatio...
Taiting Lu, Kaiyuan Lin, Mingjia Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.