Delft University of Technology

In two-view data, each view has its own covariance and a cross-view covariance links them, yet covariance neural networks handled only single-view data and could not distinguish these structures once the views were concatenated. CANE splits the model into an in-view covariance filtering stage and a cross-view covariance filtering stage, replacing the whitening and singular-vector selection of canonical correlation analysis with learnable polynomial responses on the covariance spectrum, and trains directly on the downstream task. Across seven brain-imaging and motion-sensing datasets, CANE is best or tied for best on six, reaching a mean absolute error of 4.97 years for age prediction on ADNI1, often with fewer parameters than a two-view VNN.

In two-view data, each view has its own covariance and a cross-view covariance links them, yet covariance neural networks handled only single-view data and could not distinguish these structures once the views were concatenated. CANE splits the model into an in-view covariance filtering stage and a cross-view covariance filtering stage, replacing the whitening and singular-vector selection of canonical correlation analysis with learnable polynomial responses on the covariance spectrum, and trains directly on the downstream task. Across seven brain-imaging and motion-sensing datasets, CANE is best or tied for best on six, reaching a mean absolute error of 4.97 years for age prediction on ADNI1, often with fewer parameters than a two-view VNN.

Knowledge improvement for large language models is moving from predefined incorporation pipelines to evaluation-guided updating, yet locating a weak spot does not say which intervention fits. Recursive Knowledge Improvement (RKI) organizes knowledge into graph-structured units and, each round, localizes weaknesses, estimates the model's operational knowledge state from diagnostic evidence and intervention history, selects an intervention, and re-evaluates the updated model. On HotpotEval and SafeInternalEval, RKI outperforms existing knowledge incorporation methods by 18.41 points on average, and analyses indicate knowledge states add guidance beyond weakness localization and can change across updates while the observed weakness persists.

Knowledge improvement for large language models is moving from predefined incorporation pipelines to evaluation-guided updating, yet locating a weak spot does not say which intervention fits. Recursive Knowledge Improvement (RKI) organizes knowledge into graph-structured units and, each round, localizes weaknesses, estimates the model's operational knowledge state from diagnostic evidence and intervention history, selects an intervention, and re-evaluates the updated model. On HotpotEval and SafeInternalEval, RKI outperforms existing knowledge incorporation methods by 18.41 points on average, and analyses indicate knowledge states add guidance beyond weakness localization and can change across updates while the observed weakness persists.

The long-range memory bottleneck in gated recurrent networks is traced to the gates themselves having to be learned by the same recurrent computation, and adding short-dependency samples to training brings GRU and LSTM long-dependency test accuracy from near chance back to roughly ninety percent or higher, matching or exceeding Mamba and xLSTM.

The long-range memory bottleneck in gated recurrent networks is traced to the gates themselves having to be learned by the same recurrent computation, and adding short-dependency samples to training brings GRU and LSTM long-dependency test accuracy from near chance back to roughly ninety percent or higher, matching or exceeding Mamba and xLSTM.

Using the complementary Shapley-based explainability methods SHAP and νSHAP, this work analyzes neural calibration mappings for the Heston and rough Heston models across multilayer perceptron, highway, and softmax-parametrized highway architectures, finding that short maturities and smile wings consistently dominate parameter inference and that the dominant attribution structure remains qualitatively stable across architectures, and it uses the input redundancy revealed by νSHAP to substantially reduce input dimensionality for rough Heston while matching calibration accuracy relative to the full implied volatility surface.

Using the complementary Shapley-based explainability methods SHAP and νSHAP, this work analyzes neural calibration mappings for the Heston and rough Heston models across multilayer perceptron, highway, and softmax-parametrized highway architectures, finding that short maturities and smile wings consistently dominate parameter inference and that the dominant attribution structure remains qualitatively stable across architectures, and it uses the input redundancy revealed by νSHAP to substantially reduce input dimensionality for rough Heston while matching calibration accuracy relative to the full implied volatility surface.

The authors reframe multi-agent system coordination as a data management problem and propose describing agents by their state footprint: the state they read and write across their own local context and state as well as the state of the orchestrator and external systems; they note that current orchestrators do not track this read/write state, so concurrency anomalies manifest even in simple coding tasks, and argue that MASs require database-like guarantees, yet unlike database transactions agents do not read from a fixed schema or isolated snapshot and cannot be replayed deterministically upon failure, so they can resolve conflicts semantically instead of aborting, outlining a vision for next-generation agent orchestrators and transactional interfaces for external systems.

The authors reframe multi-agent system coordination as a data management problem and propose describing agents by their state footprint: the state they read and write across their own local context and state as well as the state of the orchestrator and external systems; they note that current orchestrators do not track this read/write state, so concurrency anomalies manifest even in simple coding tasks, and argue that MASs require database-like guarantees, yet unlike database transactions agents do not read from a fixed schema or isolated snapshot and cannot be replayed deterministically upon failure, so they can resolve conflicts semantically instead of aborting, outlining a vision for next-generation agent orchestrators and transactional interfaces for external systems.

Using a 2023 workshop with 49 students as a motivating example, this paper critically reflects on the energy costs of using genAI in design education and develops a set of five alternative stances, with related actions, to support the conscious use of genAI in design education.

Using a 2023 workshop with 49 students as a motivating example, this paper critically reflects on the energy costs of using genAI in design education and develops a set of five alternative stances, with related actions, to support the conscious use of genAI in design education.