Selecting a colour palette that suits its design context (application domain, audience, and accessibility profile) affects usability, engagement, and accessibility, yet remains a difficult computational problem. Vision–language models (VLMs) have improved performance on this task but share three limitations: deterministic outputs cannot represent the variance inherent in a design brief, single-scalar training fixes the harmony–accessibility trade-off at training time, and post-hoc context filtering leaves the generator itself context-blind. We argue that these limitations stem from the output representation rather than the encoder. CAIM (Context-Aware Intelligent palette Modelling) represents palettes as a context-conditional Gaussian mixture in CIELAB whose parameters are predicted from frozen vision–language embeddings by a learned head. It refines sampled candidates under five objectives designed to target distinct and complementary mathematical features with reference-direction-based many-objective optimisation and ranks them with a context-conditioned selection rule. On four public datasets and a 3200-scenario context-rich dataset, CAIM achieves up to 23% higher predicted ratings than the strongest baseline, a 22-percentage-point gain in APCA readability over the strongest baseline, and a Pareto hypervolume 34% larger than the convex hull of baseline solutions, at 1.6 s per scenario. Modelling VLM-conditioned generation as a context-conditional distribution is promising for design tasks with inherently uncertain outputs.
Background: Complementary approach provides an opportunity for students to connect pre-class, in-class, and post-class activities. Objectives: This study examined the correlations and predictive effects of metacognition and attitude on learners' conceptual understanding in physics using a complementary approach. Method: A quasi-experimental, pretest-posttest, non-equivalent control group design was used. A sample of 173 natural science students from two Ethiopian secondary schools was randomly assigned to experimental (CAIM instruction) and control (traditional teaching) groups. Data were collected using FCCUT, MCQ, and LAS instruments and analyzed via Pearson correlations and hierarchical multiple regression at p = 0.05. Results: The two variables showed positive and statistically significant correlations with students' conceptual understanding of physics: metacognition (r = 0.30) and attitude (r = 0.31), p < 0.01. Further, both metacognition (R² = 0.15, f² = 0.08) and attitude (R² = 0.16, f² = 0.10), ΔR² = 0.08, p < 0.001, predicted 8% of the varience in conceptual understanding when CAIM was employed. Conclusion: We recommend that physics teachers could apply the CAIM when teaching physics, as it allows students to develop a positive correlation between the predictor variables and conceptual understanding, though their correlations are moderate.
