Public articles linked to the same research event.
arXiv CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.
CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.
CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.
CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.