Public articles linked to the same research event.
arXiv Analyzing 13 affective model instances spanning nine model designs, multiple scales, tasks, and training paradigms at the module level, with controlled functional analyses on representative models, the work finds a consistent yet non-exclusive functional organization in affective adaptation: under matched trainable-parameter budgets, tuning only the FFN consistently outperforms tuning only attention modules and nearly matches tuning all major Transformer projections, while gate, up, and down projections differentiate functionally after joint optimization, with gate_proj particularly prominent, motivating GET, which retains 96.2-98.0% of full-projection performance using only 19.3-24.5% as many trainable parameters.
Analyzing 13 affective model instances spanning nine model designs, multiple scales, tasks, and training paradigms at the module level, with controlled functional analyses on representative models, the work finds a consistent yet non-exclusive functional organization in affective adaptation: under matched trainable-parameter budgets, tuning only the FFN consistently outperforms tuning only attention modules and nearly matches tuning all major Transformer projections, while gate, up, and down projections differentiate functionally after joint optimization, with gate_proj particularly prominent, motivating GET, which retains 96.2-98.0% of full-projection performance using only 19.3-24.5% as many trainable parameters.
Analyzing 13 affective model instances spanning nine model designs, multiple scales, tasks, and training paradigms at the module level, with controlled functional analyses on representative models, the work finds a consistent yet non-exclusive functional organization in affective adaptation: under matched trainable-parameter budgets, tuning only the FFN consistently outperforms tuning only attention modules and nearly matches tuning all major Transformer projections, while gate, up, and down projections differentiate functionally after joint optimization, with gate_proj particularly prominent, motivating GET, which retains 96.2-98.0% of full-projection performance using only 19.3-24.5% as many trainable parameters.
Analyzing 13 affective model instances spanning nine model designs, multiple scales, tasks, and training paradigms at the module level, with controlled functional analyses on representative models, the work finds a consistent yet non-exclusive functional organization in affective adaptation: under matched trainable-parameter budgets, tuning only the FFN consistently outperforms tuning only attention modules and nearly matches tuning all major Transformer projections, while gate, up, and down projections differentiate functionally after joint optimization, with gate_proj particularly prominent, motivating GET, which retains 96.2-98.0% of full-projection performance using only 19.3-24.5% as many trainable parameters.