The rise of multimodal data, integrating text, audio, and visuals, has created new opportunities for studying multimodal tasks such as intent detection.This work investigates the effectiveness of Large Language Models (LLMs) and non-LLMs, including text-only and multimodal models, in the multimodal intent detection task.Our study reveals that Mistral-7B, a text-only LLM, outperforms most competitive multimodal models by approximately 9% on MIntRec-1 and 4% on MIntRec2.0dataset.This performance advantage comes from a strong textual bias in these datasets, where over 90% of the samples require textual input, either alone or in combination with other modalities, for correct classification.We confirm the modality bias of these datasets via human evaluation, too.Next, we propose a framework to debias the datasets, and upon debiasing, more than 70% of the samples in MIntRec-1 and more than 50% in MIntRec2.0get removed, resulting in significant performance degradation across all models, with smaller multimodal fusion models being the most affected with an accuracy drop of over 50 -60%.Further, we analyze the context-specific relevance of different modalities through empirical analysis.Our findings highlight the challenges posed by modality bias in multimodal intent datasets and emphasize the need for unbiased datasets to evaluate multimodal models effectively.We release both the code and the dataset used for this work.1

This paper describes a high-resolution 3D navigation and tracking system using magnetic field gradients, that can replace X-Ray fluoroscopy in high-precision surgeries. Monotonically varying magnetic fields in X, Y and Z directions are created in the field-of-view (FOV) to produce magnetic field gradients, which encode each spatial point uniquely. Highly miniaturized, wireless and battery-less devices, capable of measuring their local magnetic field, are designed to sense the gradient field. One such device can be attached to an implant inside the body and another to a surgical tool, such that both can simultaneously measure and communicate the magnetic field at their respective locations to an external receiver. The relative location of the two devices on a real-time display can enable precise surgical navigation without using X-Rays. A prototype device is designed consisting of a micro-chip fabricated in 65nm CMOS technology, a 3D magnetic sensor and an inductor-coil. Planar electromagnetic coils are designed for creating the 3D magnetic field gradients in a 20×20×10cm3of scalable FOV. Unambiguous and orientation-independent spatial encoding is achieved by: (i) using the gradient in the total field magnitude instead of only the Z-component; and (ii) using a combination of the gradient fields to correct for the non-linearity and non-monotonicity in X and Y gradients. The resultant X and Y FOV yield ≥90% utilization of their respective coil-span. The system is tested in vitro to demonstrate a localization accuracy of <; 100 μ m in 3D, the highest reported to the best of our knowledge.