Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-PhyQA dataset comprising Indian high school-level multimodal physics problems. To improve the LMM's performance, we experiment with two techniques, RLHF (Reinforcement Learning from Human Feedback) and Image Captioning. In image captioning, we add a detailed explanation of the diagram in each image, minimizing hallucinations and image processing errors. We further explore the integration of Reinforcement Learning from Human Feedback (RLHF) methodology inspired by the ranking approach in RLHF to enhance the human-like problem-solving abilities of the models. The RLHF approach incorporates human feedback into the learning process of LLMs, improving the model's problem-solving skills, truthfulness, and reasoning capabilities, minimizing the hallucinations in the answers, and improving the quality instead of using vanilla-supervised fine-tuned models. We employ the LLaVA open-source model to answer multimodal physics MCQs and compare the performance with and without using RLHF.

While Large Language Models (LLMs) can achieve human-level performance in various tasks, they continue to face challenges when it comes to effectively tackling multi-step physics reasoning tasks. To identify the shortcomings of existing models and facilitate further research in this area, we curated a novel dataset, MM-PhyQA, which comprises well-constructed, high schoollevel multimodal physics problems. By evaluating the performance of contemporary LLMs that are publicly available, both with and without the incorporation of multimodal elements in these problems, we aim to shed light on their capabilities. For generating answers for questions consisting of multimodal input (in this case, images and text) we employed Zero-shot prediction using GPT-4 and utilized LLaVA (LLaVA and LLaVA-1.5), the latter of which were fine-tuned on our dataset. For evaluating the performance of LLMs consisting solely of textual input, we tested the performance of the base and fine-tuned versions of the Mistral-7B and LLaMA2-7b models. We also showcased the performance of the novel Multi-Image Chain-of-Thought (MI-CoT) Prompting technique, which when used to train LLaVA-1.5 13b yielded the best results when tested on our dataset, with superior scores in most metrics and the highest accuracy of 71.65% on the test set.

Collaborative perception in multi-robot fleets is a way to incorporate the power of unity in robotic fleets. Collaborative perception refers to the collective ability of multiple entities or agents to share and integrate their sensory information for a more comprehensive understanding of their environment. In other words, it involves the collaboration and fusion of data from various sensors or sources to enhance perception and decision-making capabilities. By combining data from diverse sources, such as cameras, lidar, radar, or other sensors, the system can create a more accurate and robust representation of the environment. In this review paper, we have summarized findings from 20+ research papers on collaborative perception. Moreover, we discuss testing and evaluation frameworks commonly accepted in academia and industry for autonomous vehicles and autonomous mobile robots. Our experiments with the trivial perception module show an improvement of over 200% with collaborative perception compared to individual robot perception. Here's our GitHub repository that shows the benefits of collaborative perception: https://github.com/synapsemobility/synapseBEV

Generative AI models have revolutionized various fields by enabling the creation of realistic and diverse data samples. Among these models, diffusion models have emerged as a powerful approach for generating high-quality images, text, and audio. This survey paper provides a comprehensive overview of generative AI diffusion and legacy models, focusing on their underlying techniques, applications across different domains, and their challenges. We delve into the theoretical foundations of diffusion models, including concepts such as denoising diffusion probabilistic models (DDPM) and score-based generative modeling. Furthermore, we explore the diverse applications of these models in text-to-image, image inpainting, and image super-resolution, along with others, showcasing their potential in creative tasks and data augmentation. By synthesizing existing research and highlighting critical advancements in this field, this survey aims to provide researchers and practitioners with a comprehensive understanding of generative AI diffusion and legacy models and inspire future innovations in this exciting area of artificial intelligence.

End-to-end autonomous driving is a fully differentiable machine learning system that takes raw sensor input data and other metadata as prior information and directly outputs the ego vehicle's control signals or planned trajectories. This paper attempts to systematically review all recent Machine Learning-based techniques to perform this end-to-end task, including, but not limited to, object detection, semantic scene understanding, object tracking, trajectory predictions, trajectory planning, vehicle control, social behavior, and communications. This paper focuses on recent fully differentiable end-to-end reinforcement learning and deep learning-based techniques. Our paper also builds taxonomies of the significant approaches by sub-grouping them and showcasing their research trends. Finally, this survey highlights the open challenges and points out possible future directions to enlighten further research on the topic.

While advancing rapidly, Artificial Intelligence still falls short of human intelligence in several key aspects due to inherent limitations in current AI technologies and our understanding of cognition. Humans have an innate ability to understand context, nuances, and subtle cues in communication, which allows us to comprehend jokes, sarcasm, and metaphors. Machines struggle to interpret such contextual information accurately. Humans possess a vast repository of common-sense knowledge that helps us make logical inferences and predictions about the world. Machines lack this innate understanding and often struggle with making sense of situations that humans find trivial. In this article, we review the prospective Machine Intelligence candidates, a review from Prof. Yann LeCun, and other work that can help close this gap between human and machine intelligence. Specifically, we talk about what's lacking with the current AI techniques such as supervised learning, reinforcement learning, self-supervised learning, etc. Then we show how Hierarchical planning-based approaches can help us close that gap and deep-dive into energy-based, latent-variable methods and Joint embedding predictive architecture methods.

3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object queries (object proposals) by cross-attending multi-view features. However, individual backbone features are not updated with multi-view features and it stays as a mere collection of the output of the single-image backbone network. Therefore we propose 3M3D: A Multi-view, Multi-path, Multi-representation for 3D Object Detection where we update both multi-view features and query features to enhance the representation of the scene in both fine panoramic view and coarse global view. Firstly, we update multi-view features by multi-view axis self-attention. It will incorporate panoramic information in the multi-view features and enhance understanding of the global scene. Secondly, we update multi-view features by self-attention of the ROI (Region of Interest) windows which encodes local finer details in the features. It will help exchange the information not only along the multi-view axis but also along the other spatial dimension. Lastly, we leverage the fact of multi-representation of queries in different domains to further boost the performance. Here we use sparse floating queries along with dense BEV (Bird's Eye View) queries, which are later post-processed to filter duplicate detections. Moreover, we show performance improvements on nuScenes benchmark dataset on top of our baselines.

To plan a safe and efficient route, an autonomous vehicle should anticipate future trajectories of other agents around it. Trajectory prediction is an extremely challenging task which recently gained a lot of attention in the autonomous vehicle research community. Trajectory-prediction forecasts future state of all the dynamic agents in the scene given their current and past states. A good prediction model can prevent collisions on the road, and hence the ultimate goal for autonomous vehicles: Collision rate: collisions per Million miles. The objective of this paper is to provide an overview of the field trajectory-prediction. We categorize the relevant algorithms into different classes so that researchers can follow through the trends in the trajectory-prediction research field. Moreover we also touch upon the background knowledge required to formulate a trajectory-prediction problem.