10 papers
Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception
Aayam Bansal, Ishaan Gangwani
Cooperative perception among autonomous agents overcomes the limitations of single-agent sensing, but bandwidth constraints in vehicle-to-everything (V2X) networks require efficien…
AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse
Aayam Bansal, Ishaan Gangwani
Cooperative multi-agent methods for embodied AI are almost universally evaluated under idealized communication: zero latency, no packet loss, and unlimited bandwidth. Real-world de…
Sketch2Feedback: Grammar-in-the-Loop Framework for Rubric-Aligned Feedback on Student STEM Diagrams
Aayam Bansal
Providing timely, rubric-aligned feedback on student-drawn diagrams is a persistent challenge in STEM education. While large multimodal models (LMMs) can jointly parse images and g…
Light-Weight Benchmarks Reveal the Hidden Hardware Cost of Zero-Shot Tabular Foundation Models
Ishaan Gangwani, Aayam Bansal
Zero-shot foundation models (FMs) promise training-free prediction on tabular data, yet their hardware footprint remains poorly characterized. We present a fully reproducible bench…
Zero-Training Temporal Drift Detection for Transformer Sentiment Models: A Comprehensive Analysis on Authentic Social Media Streams
Aayam Bansal, Ishaan Gangwani
We present a comprehensive zero-training temporal drift analysis of transformer-based sentiment models validated on authentic social media data from major real-world events. Throug…
MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
Aayam Bansal, Ishaan Gangwani
Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We in…