2 papers
cs.CV2026
STEAM: Squeeze and Transform Enhanced Attention Module
Rishabh Sabharwal, Ram Samarth B B, Parikshit Singh Rathore +1
Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks (CNNs) but often increase parame…
cs.AI2026
Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback
Rishabh Sabharwal, Hongru Wang, Amos Storkey +1
Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided by feedback? To investigate…