Recent advancements in open-source Visual Language Models (VLMs) such as LLaVA, Qwen-VL, and Llama have catalyzed extensive research on their integration with diverse systems. The internet-scale general knowledge encapsulated within these models presents significant opportunities for enhancing autonomous driving perception, prediction, and planning capabilities. In this paper we propose VLAD, a vision-language autonomous driving model, which integrates a fine-tuned VLM with VAD, a state-of-the-art end-to-end system. We implement a specialized fine-tuning approach using custom question-answer datasets designed specifically to improve the spatial reasoning capabilities of the model. The enhanced VLM generates high-level navigational commands that VAD subsequently processes to guide vehicle operation. Additionally, our system produces interpretable natural language explanations of driving decisions, thereby increasing transparency and trustworthiness of the traditionally black-box end-to-end architecture. Comprehensive evaluation on the real-world nuScenes dataset demonstrates that our integrated system reduces average collision rates by 31.82% compared to baseline methodologies, establishing a new benchmark for VLM-augmented autonomous driving systems.

While methods based on Vision Transformers (ViT) have achieved state-of-the-art performance in many domains, they have not yet been applied successfully in the domain of writer retrieval. The field is dominated by methods using handcrafted features or features extracted from Convolutional Neural Networks. In this work, we bridge this gap and present a novel method that extracts features from a ViT and aggregates them using VLAD encoding. The model is trained in a self-supervised fashion without any need for labels. We show that extracting local foreground features is superior to using the ViT's class token in the context of writer retrieval. We evaluate our method on two historical document collections. We set a new state-at-of-art performance on the Historical-WI dataset (83.1\% mAP), and the HisIR19 dataset (95.0\% mAP). Additionally, we demonstrate that our ViT feature extractor can be directly applied to modern datasets such as the CVL database (98.6\% mAP) without any fine-tuning.

Adversarial machine learning attacks on video action recognition models is a growing research area and many effective attacks were introduced in recent years. These attacks show that action recognition models can be breached in many ways. Hence using these models in practice raises significant security concerns. However, there are very few works which focus on defending against or detecting attacks. In this work, we propose a novel universal detection method which is compatible with any action recognition model. In our extensive experiments, we show that our method consistently detects various attacks against different target models with high true positive rates while satisfying very low false positive rates. Tested against four state-of-the-art attacks targeting four action recognition models, the proposed detector achieves an average AUC of 0.911 over 16 test cases while the best performance achieved by the existing detectors is 0.645 average AUC. This 41.2% improvement is enabled by the robustness of the proposed detector to varying attack methods and target models. The lowest AUC achieved by our detector across the 16 test cases is 0.837 while the competing detector's performance drops as low as 0.211. We also show that the proposed detector is robust to varying attack strengths. In addition, we analyze our method's real-time performance with different hardware setups to demonstrate its potential as a practical defense mechanism.

We propose Dirichlet Simplex Nest, a class of probabilistic models suitable for a variety of data types, and develop fast and provably accurate inference algorithms by accounting for the model's convex geometry and low dimensional simplicial structure. By exploiting the connection to Voronoi tessellation and properties of Dirichlet distribution, the proposed inference algorithm is shown to achieve consistency and strong error bound guarantees on a range of model settings and data distributions. The effectiveness of our model and the learning algorithm is demonstrated by simulations and by analyses of text and financial data.

A 2017 Tractica report on the natural language processing (NLP) market estimates the total NLP software, hardware, and services market opportunity to be around $22.3 billion by 2025. The report also forecasts that NLP software solutions leveraging AI will see a market growth from $136 million in 2016 to $5.4 billion by 2025. In order to shed more light on the growing applications of NLP solutions, Dan Faggella, the CEO of TechEmergence, converses with Vlad Sejnoha, the CTO of Nuance Communications, an organization offering AI and NLP solutions in voice, natural language understanding, reasoning and systems integration. Vlad Sejnoha has been the Senior Vice President and CTO at Nuance since 2001. He holds a Masters degree in Electrical Engineering from McGill University. Vlad has been working in the field of NLP and speech recognition for over 30 years and holds 22 patents to date.

The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech translation or image captioning have so far ignored the geometry of the latent embedding, that they iteratively learn. We propose the information geometric Seq2Seq (GeoSeq2Seq) network which abridges the gap between deep recurrent neural networks and information geometry. Specifically, the latent embedding offered by a recurrent network is encoded as a Fisher kernel of a parametric Gaussian Mixture Model, a formalism common in computer vision. We utilise such a network to predict the shortest routes between two nodes of a graph by learning the adjacency matrix using the GeoSeq2Seq formalism; our results show that for such a problem the probabilistic representation of the latent embedding supersedes the non-probabilistic embedding by 10-15\%.

The event took place on Thursday, September 22nd, 2016. We asked startup vendors and representatives from the organization team about these trends. Kevin Kelly was right when he predicted that the business plans of the next 10,000 startups were easy to forecast: »take X and add AI«. Computers that see and listen, think and predict are already making a difference across industries. Artificial intelligence can automate processes, reduce costs and improve customer experience. Corporations need to leverage those machine learning technologies or risk being replaced by'smarter disruptors.' [Tomasz Rudolf, CEO D-RAFT] For sure, we now have the technology (measured in computer power and algorithms) that is able to achieve great progress every year. But the most important difference is that AI started to finance itself. A great recent example is about using DeepMind's work on reinforcement learning to reduce Google's Data Center cooling bill by 40%. The biggest difference is unsupervised learning and the availability of "cheap" GPU power. That's why we see so many startups rising in the field of AI. I believe this is the main reason that we are entering the machine learning era.

In computer vision, a complex entity such as an image or video is often represented as a set of instance vectors, which are extracted from different parts of that entity. Thus, it is essential to design a representation to encode information in a set of instances robustly. Existing methods such as FV and VLAD are designed based on a generative perspective, and their performances fluctuate when difference types of instance vectors are used (i.e., they are not robust). The proposed D3 method effectively compares two sets as two distributions, and proposes a directional total variation distance (DTVD) to measure their dissimilarity. Furthermore, a robust classifier-based method is proposed to estimate DTVD robustly, and to efficiently represent these sets. D3 is evaluated in action and image recognition tasks. It achieves excellent robustness, accuracy and speed.