Indian Institute of Science Bangalore

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.

In head and neck squamous cell carcinoma the partial EMT gene list is expressed by both malignant cells and fibroblasts, yet it has been scored only in bulk tumours. Dividing its 100 genes by the cells that express them shows bulk co-expression is dominated by the stromal arm, so standard pEMT scores mainly measure stroma; a single-cell pseudobulk classifier and a 12-gene malignant core recover the malignant arm in any bulk transcriptome. Among 40 patients given platinum plus cetuximab, both malignant measures were higher in those with long progression-free survival (area under the curve 0.78 and 0.82) and the stromal core was not, but the malignant arm could not be separated from the Basal subtype, which discriminated better (0.93).

In head and neck squamous cell carcinoma the partial EMT gene list is expressed by both malignant cells and fibroblasts, yet it has been scored only in bulk tumours. Dividing its 100 genes by the cells that express them shows bulk co-expression is dominated by the stromal arm, so standard pEMT scores mainly measure stroma; a single-cell pseudobulk classifier and a 12-gene malignant core recover the malignant arm in any bulk transcriptome. Among 40 patients given platinum plus cetuximab, both malignant measures were higher in those with long progression-free survival (area under the curve 0.78 and 0.82) and the stromal core was not, but the malignant arm could not be separated from the Basal subtype, which discriminated better (0.93).

AeroEval is an agent-assisted middleware that validates AI-generated drone missions in stages between generation and execution: deterministic syntax and platform-API checks plus an intent-validation agent screen the program, accepted candidates run in a physics-based simulator, and a numerical trajectory comparator or a context-grounded agent then evaluates obstacle avoidance, altitude, coverage, orientation, and event-driven transitions, returning structured failure diagnoses for iterative regeneration; it raises navigation success from 11 to 19 of 20 tasks and aggregate analytical run-level success from 0.30 to 0.90.

AeroEval is an agent-assisted middleware that validates AI-generated drone missions in stages between generation and execution: deterministic syntax and platform-API checks plus an intent-validation agent screen the program, accepted candidates run in a physics-based simulator, and a numerical trajectory comparator or a context-grounded agent then evaluates obstacle avoidance, altitude, coverage, orientation, and event-driven transitions, returning structured failure diagnoses for iterative regeneration; it raises navigation success from 11 to 19 of 20 tasks and aggregate analytical run-level success from 0.30 to 0.90.

The work introduces architectural sampling, a training-free method that generates candidates through distinct forward computations by reusing selected blocks of decoder layers in a frozen model; across five Qwen checkpoints and twelve multimodal benchmarks it improves pass@9 over standard-path temperature sampling by 6.58 percentage points on average at the same nine-candidate budget, with the strongest gains from reusing early layers, candidate-coverage improvement persisting under greedy decoding, lower lexical overlap among candidates, and higher accuracy when the candidates serve as rollouts for label-free test-time reinforcement learning.

The work introduces architectural sampling, a training-free method that generates candidates through distinct forward computations by reusing selected blocks of decoder layers in a frozen model; across five Qwen checkpoints and twelve multimodal benchmarks it improves pass@9 over standard-path temperature sampling by 6.58 percentage points on average at the same nine-candidate budget, with the strongest gains from reusing early layers, candidate-coverage improvement persisting under greedy decoding, lower lexical overlap among candidates, and higher accuracy when the candidates serve as rollouts for label-free test-time reinforcement learning.